plugins

---
description: "Bring a machine's plugin fleet current on demand: marketplace refresh, update the plugins that actually load (including in-repo project/local-scope installs), install new catalog plugins per policy, detect scope divergence, and surface (never silently fix) drift, with a terse actionable report; refuses to downgrade by default. Actions: sync (default, mutating), audit (read-only dry run), converge (explicit scope consolidation). Use when: 'sync plugins', 'update my plugins', 'are my plugins current', 'check plugin drift', 'converge plugin scopes', or before relying on a plugin that might be stale."
argument-hint: "[sync|audit|converge] [<marketplace>|all] [--allow-downgrade]"
user-invocable: true
disable-model-invocation: true
metadata:
  workflow-stage: operator
  summary: Bring the machine's plugin fleet current. Refresh, update, install per policy
  cadence: weekly
---

**Arguments.** `[sync|audit|converge] [<marketplace>|all] [--allow-downgrade]`. Full form: [action] [<marketplace>|all] [--allow-downgrade]. Actions: sync (default; alias update), audit, converge

## Variables

Arguments: `$ARGUMENTS`

## Scope

Guarantees that the plugins which actually load, for the machine's user scope, and for any repo
you're standing in with its own project/local-scope installs, are the latest published versions of
everything the marketplace offers, and surfaces any state where something older or unintended is
what really runs.

Distinct from Claude Code's own background `autoUpdate`, which we treat as a background refresh of
already-installed plugins, never a substitute for this skill
([context/scope-semantics.md](context/scope-semantics.md) holds that reading and its pointer). This
skill covers what we do not rely on `autoUpdate` for: installing new catalog plugins, checking
`enabledPlugins` completeness, detecting and reporting scope divergence, and running on demand.

Distinct from `harness-config`'s `audit` skill's plugin-drift check: that check compares a project's
committed `enabledPlugins` against a marketplace's *upstream* `marketplace.json` (orphan/new/rename
plugin names). This skill compares the *local, already-installed* state (`installed_plugins.json`,
per-scope `enabledPlugins`) against the *local* marketplace catalog, a different axis (install/scope
completeness, not settings-vs-upstream drift).

**Never silently fixes drift it finds.** `sync` mutates only via the documented CLI actions below,
and never writes a committed `.claude/settings.json`: its Step 5 enables automatically only at
`user` and `local` scope, and reports a `project`-scope gap rather than filling it, because `sync`
has no autonomous-session abort behind which a confirm would mean anything. After Step 4 installs
anything, `sync` may reorder keys in user-scope `~/.claude/settings.json` (machine-local, already
written by `claude plugin install -s user`) so the map stays alphabetical; it never reorders a
project-scope map. `converge` is the one action that can touch committed settings, and only after
an explicit per-plugin confirm. See [context/scope-semantics.md](context/scope-semantics.md) for
which CLI calls write that file.

**For `sync` and `audit`, the script computes every number and the model reports it.** Steps 1
through 5b and the Step 6 render are one `sync-run.sh` call; the digest and the rendered report
are the record, and the model adds the reload guidance and answers questions. Nothing in the
report is retyped, recounted, or re-derived by the model. `converge` follows the same rule for
its plan: `converge-plan.sh` computes every row's strategy, command and class, grouped by path, and
the model presents it and runs only what the user confirms.

**The skill never branches on the host to change its algorithm or its report.** There is no
cloud-versus-local branch, and no detection of or coordination with a repository's bootstrap hook:
the same steps run and the same report renders wherever the skill is invoked. Two things this
invariant does not cover, because they are not algorithm or report branches: the destructive-tier
autonomy abort `converge` performs before touching anything (`CLAUDE_CODE_REMOTE`, `/loop`,
`/schedule`; see [context/converge.md](context/converge.md)), and the platform-portability
detection in `fleet-state.sh` (`$OSTYPE` for MSYS and Cygwin path forms), which changes how a path
is spelled and never what is computed.

## Action Router

Parse `$ARGUMENTS` for the action (first token) and an optional marketplace target (second token:
a marketplace name, or `all`).

`--allow-downgrade` is position-independent: remove it from `$ARGUMENTS` first, then apply the
first-token / second-token parse to what remains, so it reads the same before, between, or after the
other two. It applies to `sync` only, and it opts that run into moving an install backward when the
marketplace catalog reads lower than what is installed. `audit` ignores the flag and says so in its
report: a read-only run issues no update either way, and its prediction already names the withheld
downgrades. See [context/sync.md](context/sync.md)'s "Downgrade guard".

This table is an index, not a substitute: read the linked detail file before executing any action,
except `sync` and `audit`, which one script runs and which load their file on the triggers under
"Running `sync` and `audit`". Each Description names the territory an action covers, never its algorithm, the steps, their
ordering, and their failure handling live only in the linked file.

One block below is a deliberate exception to that index-only rule and has to live in the hub
rather than in a spoke: the **`install_new` render**, because we rely on `${user_config.*}` being
substituted only when Claude Code renders the *skill*; a spoke opened later as a file read is plain
bytes, so the same token in a spoke would arrive as a literal placeholder with no error to warn
anyone.
See [context/gotchas.md](context/gotchas.md). The Report section below is a pointer: the report
itself is rendered by the script.

| Action | Mutates | Description | Detail |
|---|---|---|---|
| `sync` (default) | Yes. CLI only | Marketplace, install, and enable-state maintenance for the effective fleet | [context/sync.md](context/sync.md) |
| `audit` | No | Same algorithm as `sync`, every mutating CLI call replaced with a prediction; the reads those calls sit beside still run | "Action: audit" below |
| `converge` | Yes. Can rewrite committed settings after confirm | Cross-scope divergence reconciliation, preview- and confirm-gated | [context/converge.md](context/converge.md) |

Bare invocation (no arguments) → `sync` against the default marketplace. `update` is an alias for
`sync`. `help` or an unrecognized action → show this table.

## Running `sync` and `audit`

Both actions execute Steps 1 through 5b and render Step 6's report as ONE bundled script call:
it prints the JSON digest, then the report. The step sequence, and the reason behind every step,
stay in [context/sync.md](context/sync.md); the script is bound to that file.

1. **Run it.** Substitute the marketplace target, the policy, and the flags into this command. The
   journal root is written here because we rely on `${CLAUDE_PLUGIN_DATA}` resolving in skill
   content and **not** in a `context/*.md` spoke, which is read raw (see "Spoke paths" below):

   ```bash
   "${CLAUDE_PLUGIN_ROOT}"/skills/plugins/scripts/sync-run.sh \
     [--marketplace <name> | --all] \
     --journal-root "${CLAUDE_PLUGIN_DATA}/plugins-sync/runs" \
     --install-new <policy> [--allow-downgrade] --render
   ```

   `audit` is the same command with `--audit` instead of `--journal-root` (it writes to a scratch
   directory it deletes) and never `--allow-downgrade`, which it ignores and says so.

   `<policy>` is the word from the **Configured value** line under "userConfig: `install_new`"
   below: `all`, `none`, or `ask`, and `ask` when that line still shows the unset placeholder
   token. Pass the WORD, never the token: a placeholder inside a command is a shell substitution
   error, not a policy. Any other value is treated as `ask` and named back in the digest's
   `install_new_invalid` so the report can flag it, on the first pass and on an `--only-install`
   re-entry alike.

2. **Read the output.** The first line is one compact JSON digest, also written to
   `<run_dir>/digest.json`; after a blank line comes the rendered report, also written to
   `<run_dir>/report.txt`. The digest carries a `run_dir` that holds every snapshot and the
   journal, and the fields the `ask` re-entry needs.

3. **Resolve an `ask` install gap.** When a block has a non-empty `install_gap` and
   `stopped_before_install: true` (the report says so under `Action needed`), run the chunked
   "install and enable" offer from
   [context/sync-install-enable.md](context/sync-install-enable.md), then re-enter for Steps 4 and
   5 against the same run. The re-entry installs each pick and enables any the CLI installed
   disabled by default:

   ```bash
   "${CLAUDE_PLUGIN_ROOT}"/skills/plugins/scripts/sync-run.sh \
     --only-install "<the ids the user picked, comma-separated>" --run-dir "<the digest's run_dir>" --render
   ```

   An empty id list is legal and means "install nothing, still complete Step 5". A dismissed or
   unanswered chunk declines only its own ids: leave them out of the list and keep the picks from answered chunks. When nothing was answered, the list is empty: re-enter with `--only-install ""`, and the report lists
   the declined gap under `Action needed`. The report that
   call prints supersedes the first one and covers the whole run. When the first pass stopped
   before install it skipped the cache-content check, and this re-entry runs that check after the
   installs; otherwise the re-entry reuses the finding the first pass wrote.

4. **Report.** Paste the rendered report and append the one model-owned line; see the Report
   section below.

Load [context/sync.md](context/sync.md) when a digest carries errors, a non-empty gap, a catalog
regression, a cache-content finding, or a nonzero `moved_during_run` or `noop_unverified` count
(plugins that moved during the run under an update call that reported them current, or
already-current answers the snapshots could not confirm), and when the user asks why a step behaved
the way it did.

## Marketplace resolution

No hardcoded marketplace name anywhere in this skill. Every action resolves its target the same way:

- No marketplace argument → the default: the marketplace this plugin (`harness-ops`) was itself
  installed from, resolved dynamically by `fleet-state.sh` (joins `${CLAUDE_PLUGIN_ROOT}` against
  `installed_plugins.json`'s install records, never a hardcoded name).
- `<marketplace-name>` argument → that marketplace only.
- `all` argument → every marketplace in `known_marketplaces.json`; per-marketplace failures are
  reported inline and never abort the sweep (see [context/sync.md](context/sync.md)). **`all` also
  multiplies the `install_new` policy across every catalog**: under a rendered policy of `all` this
  target installs every plugin published in every known marketplace. Confirm the resolved install
  gap with a human first, per "userConfig: `install_new`" below.

## State inspection

Every action reads the fleet through the bundled read-only `fleet-state.sh`, checks cache content
through `cache-content-check.sh`, and reorders a user-scope `enabledPlugins` map only through
`normalize-enabled-plugins.sh`. Never hand-parse `installed_plugins.json`,
`known_marketplaces.json`, or a settings file, never write them, and never hand-write a `jq`
extraction where a script's `--ids` form exists. The one sanctioned exception is `converge`'s
committed-enable check ([context/converge.md](context/converge.md) Step 2): a read-only look at the
`enabledPlugins` keys of a tracked project settings file, which `converge-plan.sh` makes and the
model does not. `sync-run.sh` calls all three during `sync` and `audit`. Alongside them `scripts/jq-capture.sh` ships as a sourced library, never invoked: it
carries the CR-stripping `jq` capture and the JSON string encoder that `fleet-state.sh`,
`cache-content-check.sh`, and `sync-run.sh` each source from their own directory.
Read [context/script-contracts.md](context/script-contracts.md) when a step misbehaves,
when `converge` needs an id list, or before invoking one of the scripts from anywhere other than
`sync-run.sh`; it carries each script's invocation forms and the `\r` rule behind `--ids`.

## Action: audit

Read-only dry run of what `sync` (and, where relevant, `converge`) would do. Run the full algorithm
in [context/sync.md](context/sync.md) with every mutating CLI call replaced by "would run: `<command>`"
in the report. Call `fleet-state.sh`, compute the same install/enable/divergence deltas, but issue
**zero** `plugin install|update|uninstall|marketplace update` invocations. Predict `converge`'s
per-plugin intent (context/converge.md's preview step) the same way, without executing it. An
`audit` run writes no state file (`installed_plugins.json`, `known_marketplaces.json`, committed
settings); a concurrent session or background `autoUpdate` sweep can still change them while it
runs.

**A read that sits beside a mutating call is still taken.** Step 1 is the case that matters: its
pre-refresh `fleet-state.sh` snapshot is a read and `audit` takes it, and only the
`claude plugin marketplace update` beside it becomes a prediction. That snapshot is the first link in
the catalog regression check's chain, so an `audit` that skipped it would start the check at `pre`
and lose the interval that isolates the refresh point. See [context/sync.md](context/sync.md) Step 1.

`audit` runs the same steps, and those steps write reports from Step 1's snapshot onward, so it does
write them: to a throwaway `mktemp -d` scratch directory, created before Step 1 and deleted when the
run ends, never to the durable run journal under this plugin's data directory. That keeps one algorithm
for both actions while leaving nothing behind, which is what "mutates nothing" means here. See
[context/sync.md](context/sync.md)'s "Run journal" section.

`audit` ignores `--allow-downgrade` and says so when the flag is passed: it issues no update in
either case, and it predicts `Would withhold: <N> downgrade(s)` beside `Would update` regardless.
See [context/sync.md](context/sync.md) Step 3.

Because `audit` issues no `marketplace update`, its Step 3 prediction is computed against an
**unrefreshed** catalog and is therefore a lower bound on what `sync` would update. Report it as one,
carrying the catalog's `lastUpdated`. See [context/sync.md](context/sync.md) Step 3. An `audit`
that predicts zero updates has not established that the fleet is current.

## Report

Step 6 is rendered by the script. `sync-run.sh --render` prints the fixed-section report after the
digest line, every run writes the same text to `<run_dir>/report.txt`, and
`jq -r -f "${CLAUDE_PLUGIN_ROOT}"/skills/plugins/scripts/render-report.jq <run_dir>/digest.json`
reproduces it from a run directory later. Every section, conditional row, annotation, and
`Action needed` bullet is a function of digest fields, which is what keeps a number, an id, or a
scope from being misstated between the run and the report: the `Marketplace:` line with its
three-way `autoUpdate` slot (`on`; `off` with the suggestion to enable it; `unreadable` for a
`null`, never rendered as off), whose status reads `needs update` only for refresh, update and
failure state (a failed refresh or CLI call, or an error; in `audit`, an update, install or enable `sync`
would make), `source checkout behind <upstream>` when a `directory` source's git checkout is behind
its upstream, and `current` otherwise, followed by `, N action(s) pending` when work is left to a
person (an install declined, skipped by policy or held for the `ask` prompt, an unfilled or project-scope enable, an
install left not enabled, a delisted plugin, a withheld downgrade), so
`current, 1 action(s) pending` is a fleet with nothing to update and one such action. Each pending
action is an `Action needed` bullet, except `audit`'s withheld downgrades, counted once as their
`Would withhold:` row; the `source:` row under
it for a `directory` source (branch, upstream, ahead/behind as of the checkout's last fetch, modified
tracked files, or why freshness was not checked; the run never fetches or pulls the checkout); the fixed `In-repo:` row in its three variants (`skipped` naming
the cwd when no project root resolved, `0` naming a root with no project/local installs, and the
counted variant, forward moves only); `Updated:` (forward moves and pairs flagged
`(direction unknown)`) and `Downgraded:` (a backward move that happened during the run says so); `Moved during this run:` (ids
whose update call the CLI answered "already at the latest version" while the run's snapshots show
their version changed, which the run did not do and does not attribute; with a `Not verified:` row
for already-current answers the snapshots could not confirm); `Catalog regression:`; `Installed:` with the policy-`all`
recurrence clause; `Normalized:`; `Enabled:`; the `Divergences:` split, led by this project's count
when a root resolved, with one sub-line per project path naming its record count and up to three
ids (`+K more` past that); the self-update note when this plugin's install record moved during the run; the stale project
records and user-scope cache content sections; the `Timing:` row (the marketplace total, its slowest step,
and the seconds outside the named steps, with the clock's resolution; a measurement with no threshold); and `Action needed` (a behind `directory` checkout with the
`git -C <path> pull --ff-only` to run and the marketplace to resync, install and enable gaps, failed CLI calls, user-scope orphans, installs that left userConfig options unset,
installs the CLI reported as disabled by default that this run did not enable, plugins absent from the catalog (installed, or
only enabled in settings),
updated plugins whose installed build declares a monitor, reorder refusals, an unsorted
project-scope map, withheld downgrades with both versions and the likely cause, and every error).
In `audit` mode every call `sync` would make carries the `would run:` prefix, and a remedy `sync`
never runs itself (the `git -C … pull --ff-only`, a project-scope enable) reads the same as in
`sync`, unprefixed. `Would withhold:` sits beside `Would update:` whether or not a downgrade was
found; `--allow-downgrade` is named as ignored. Each shape is pinned to a golden file under `scripts/fixtures/render/` by
`scripts/sync-run.test.sh`.

Paste the render as printed. Do not restate a number, an id, a scope, or a count it already
carries, and do not add rows: a row the render omitted is a row whose digest field was empty, which
is not proof that nothing happened. The render lists only what the run's snapshots establish, so the
initial report may add one caveat line when something in the run suggests more than it shows (a
`Not verified:` row, or `Moved during this run:` ids with a cause the user may ask about): state
what the report cannot establish, never a cause. Follow-up answers from the run directory stay
allowed. Per
marketplace in `all` mode the whole block repeats, because Steps 2 through 5 run once per
marketplace; the trailing `Run journal:` and `Timing:` lines cover the invocation.

**The one line the model owns is the reload guidance**, appended after the render as a two-step
rather than as a prediction about which case will trigger it: recommend bare `/reload-plugins`,
and `/reload-plugins --force` only when the bare command warns. Do not present any one cause as the
sole trigger of that warning, and do not tell the user `--force` would be wrong when the bare
command has already warned them. Never recommend `--force` pre-emptively alongside every reload: we
treat it as opting into a real token cost the bare command declines to pay on its own.
[context/scope-semantics.md](context/scope-semantics.md) "`/reload-plugins`: bare by default,
`--force` for the MCP-cache-invalidation case" holds the pointers and dates. Monitors are already
covered: the render's `Action needed` names each updated plugin whose installed build declares one.
[context/sync.md](context/sync.md) "Name the monitors" holds what that bullet says and where it was
read, so the reload line does not restate it. After the line, answer follow-up questions from the digest
and the run directory it names; load [context/sync.md](context/sync.md) when a question is about
why a step behaved the way it did.

(We observed a plugin updated mid-session keep resolving to the previous version's path, which is
what the self-update note reports: Claude Code 2.1.240, not re-run on 2.1.261 because it needs an
interactive session. The record is in [context/gotchas.md](context/gotchas.md).)

## Stale project records and cache content

Both are findings the render reports and this skill never fixes: a project/local record whose
`projectPath` is not present on this machine is named in its own section, never counted as a
divergence, never suppressed, and never reaped; a cache directory whose files disagree with the
recorded commit is named with the proved remediation, never repaired. Read
[context/stale-records-cache-content.md](context/stale-records-cache-content.md) when
`stale_project_records.total > 0` or `cache_content.stale_content > 0`, or when the user asks why
either section reads as it does.

## userConfig: `install_new`

Controls new-catalog-plugin install policy during `sync`. Ships as a `string` whose `options`
picker lists the three values below, default `"ask"`. This skill still validates the value,
because one set by hand in `settings.json` never passes through the picker ([context/scope-semantics.md](context/scope-semantics.md) holds the option-schema
record; for option types and fixed options, see
[User configuration](https://code.claude.com/docs/en/plugins/manifest-reference#user-configuration) and
[Limit a field to fixed options](https://code.claude.com/docs/en/plugins/manifest-reference#limit-a-field-to-fixed-options)):

- `ask` (default). Offer every not-yet-installed catalog plugin in `AskUserQuestion` chunks of at
  most 4 options per question and at most 4 questions per call, with a further call past 16, each
  chunk's question text distinct (answers are keyed by it). A chunk of 1, whether a gap of 1 or
  the one left over from a gap of 5, 9, 13 and so on, is a single-select Install/Skip question
  with no hand-added Other option. The limits are the tool's, per
  [Handle approvals and user input](https://code.claude.com/docs/en/agent-sdk/user-input.md)
  (as of 2026-10-18; recheck if that page changes them). Then install and enable each pick,
  including one the CLI installs disabled by default. An unanswered or dismissed chunk counts as
  declined
- `all`. Install every not-yet-installed catalog plugin automatically; one the CLI installs
  disabled by default stays off and is reported
- `none`. Report them in "Action needed" only, never install

Any explicitly-set value other than these three is invalid; treat it as `ask` and note the invalid
value in the report.

**`all` is scoped to the marketplace target, and the target is what makes it safe or catastrophic.**
Against the default marketplace, the one whose fleet the operator curates, the gap is normally zero
or a handful and `all` is the intended convenience. Against a multi-marketplace target (`all`, or a
named third-party catalog) the same word means "install every plugin published in every catalog this
machine knows about." One observed run installed 2,231 plugins before it was killed; see
[context/gotchas.md](context/gotchas.md)'s "`--all` with `install_new: all` is a mass install of
every catalog". **When the marketplace target is `all` and the rendered policy is `all`, do not
proceed unattended:** resolve the total install gap first (one `audit all`, or `fleet-state.sh
--marketplace <name> --ids missing-user-install` per marketplace, which is the selector
`sync-run.sh` itself projects for Step 4), state the number, and get an explicit human yes. Treat the
configured value as written with the operator's own marketplace in mind, and downgrade to `ask` when
no human is present to receive the count.

**Configured value: `${user_config.install_new}`**. We treat this line as rendering the configured
word into the skill content before the model sees it, but **only when the key is explicitly set**
in one of the three sources this skill reads `pluginConfigs` from: user settings
(`~/.claude/settings.json`), `--settings`, or managed settings, with precedence managed →
`--settings` → user. A project's `.claude/settings.json` or `.claude/settings.local.json` entry does
nothing at all, and declaring the option in `plugin.json` alone does not make its value readable
here either. See [context/scope-semantics.md](context/scope-semantics.md) for the read path, its
pointer, and why it differs from `enabledPlugins`, which this same skill reads from project and
local scope.

The manifest's `"default": "ask"` is **not** substituted for an unset key: our probe saw the render
leave the placeholder token unchanged while a sibling key set in `~/.claude/settings.json` and
`${CLAUDE_PLUGIN_ROOT}` both substituted in the same render. That is a probed claim, not a
documented one, and it stays pointed at its dated record: the probe, its as-of date and CLI version,
the docs pointer for the `default` field and the substitution surfaces, the recheck trigger, the
`pluginConfigs` payload shape, and the probe recipe are in
[context/scope-semantics.md](context/scope-semantics.md) "`userConfig`: an unset key renders the
literal placeholder". Read it when the rendered value looks wrong or before re-running the probe.
Substitution into content happens in what Claude Code renders, and never in a file a spoke read
returns, which is why the **Configured value** line lives here and cannot move to a spoke. So for
the common default-config user, with no `pluginConfigs` set anywhere, the **Configured value** line
above still shows that literal placeholder token, not `ask`.

Read that literal placeholder token as the **expected unset state → use the default `ask`**, and do NOT
report it as an invalid value. Only a rendered value that is a real word other than
`ask`/`all`/`none` (i.e. the key *was* set, to something unsupported) is the invalid-value case worth
flagging. Sync's Step 4 branches on the **Configured value** line's rendered value, or on the `ask`
default when that render is still the placeholder token, not on the option's name or description above.

## Spoke paths

The `context/` files write this skill's directory as `<skill-dir>`, which is `${CLAUDE_SKILL_DIR}`.
Put that path in place of the placeholder before running a command or writing it into a brief. We
never put a `${…}` token in those files: we do not rely on one being substituted in a file read
through the Read tool, or on the Bash tool's environment carrying `CLAUDE_SKILL_DIR`.

- **Pointer**: for where each `${…}` reference resolves, see
  [Where each variable resolves](https://code.claude.com/docs/en/plugins/manifest-reference#where-each-variable-resolves).
- **As of**: 2026-10-07
- **Recheck trigger**: that table adds supporting files to where a `${…}` reference resolves.

## Next

/harness-ops:prerequisites lists which external binaries the enabled fleet is missing.

## Reference index. Load on demand

| File | Load when |
|---|---|
| [context/sync.md](context/sync.md) | A `sync` or `audit` digest meets a trigger under "Running `sync` and `audit`", or the user asks why a step behaved as it did; it is the step sequence both actions execute, and the script is bound to it. |
| [context/sync-install-enable.md](context/sync-install-enable.md) | A digest block has a non-empty `install_gap` or `enable_gap`, or `install_enable_deferred: true`. Both gaps are empty on a current fleet. |
| [context/converge.md](context/converge.md) | Running `converge`, the only action that may rewrite a committed settings file. |
| [context/stale-records-cache-content.md](context/stale-records-cache-content.md) | The digest's `stale_project_records.total` or `cache_content.stale_content` is above 0, or the user asks why either section reads as it does. |
| [context/script-contracts.md](context/script-contracts.md) | A step misbehaves, `converge` needs an id list, or a caller other than `sync-run.sh` is about to invoke `fleet-state.sh`, `cache-content-check.sh`, or `normalize-enabled-plugins.sh`. |
| [context/scope-semantics.md](context/scope-semantics.md) | A scope, version, or reload claim needs its verified source before you act on it; also the dated `userConfig` unset-key probe record. |
| [context/gotchas.md](context/gotchas.md) | A run failed in a way the steps do not explain, or a safeguard looks removable. |

• SKILL.md 28 KB
• context/converge.md 21 KB
• context/gotchas.md 32 KB
• context/scope-semantics.md 43 KB
• context/script-contracts.md 5 KB
• context/stale-records-cache-content.md 10 KB
• context/sync-install-enable.md 18 KB
• context/sync.md 66 KB
• evals/evals.json 30 KB
• scripts/cache-content-check.sh 48 KB
• scripts/cache-content-check.test.sh 53 KB
• scripts/converge-plan.sh 15 KB
• scripts/converge-plan.test.sh 10 KB
• scripts/fleet-state.sh 79 KB
• scripts/fleet-state.test.sh 149 KB
• scripts/jq-capture.sh 3 KB
• scripts/normalize-enabled-plugins.sh 6 KB
• scripts/normalize-enabled-plugins.test.sh 7 KB
• scripts/render-report.jq 27 KB
• scripts/sync-run.sh 107 KB
• scripts/sync-run.test.sh 165 KB
• scripts/fixtures/installed_plugins.sample.json 1 KB
• scripts/fixtures/known_marketplaces.sample.json 1 KB
• scripts/fixtures/render/all-with-refresh-failure.txt 1 KB
• scripts/fixtures/render/ask-reentry-disabled-enabled.txt 1 KB
• scripts/fixtures/render/ask-reentry-installed.txt 1 KB
• scripts/fixtures/render/ask-reentry-none-picked.txt 1 KB
• scripts/fixtures/render/ask-stopped-before-install.txt 1 KB
• scripts/fixtures/render/audit-would-run.txt 1 KB
• scripts/fixtures/render/clean-current.txt 1 KB
• scripts/fixtures/render/directory-source-behind.txt 1 KB
• scripts/fixtures/render/divergence-by-path-no-root.txt 1 KB
• scripts/fixtures/render/divergence-split-no-root.txt 1 KB
• scripts/fixtures/render/divergence-split-project-root.txt 1 KB
• scripts/fixtures/render/installed-all-disabled.txt 1 KB
• scripts/fixtures/render/installed-unset-user-config.txt 1 KB
• scripts/fixtures/render/moved-during-run.txt 1 KB
• scripts/fixtures/render/self-update-not-first.txt 1 KB
• scripts/fixtures/render/stale-records-cache-content.txt 2 KB
• scripts/fixtures/render/withheld-downgrade.txt 1 KB