Skip to content
Skills Library
AI & agents · Automation

setup

/setup

Post-install setup for the research plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks and merge its own permissions.allow and permissions.deny entries into ~/.claude/settings.json. TRIGGER when: user installed or upgraded the research plugin and its rules are not loading, or its deny rules are not blocking; phrases: 'set up research', 'research rules not loading', 'merge research permissions', 'after upgrading research'. SKIP: statusLine/TEAM_PROTOCOL/plugin-cache setup (use /f

Author
Borda ↗
Repository
AI-Rig ↗
Licence
Apache-2.0
Last repository change
22.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 22.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Post-install setup for the research plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks and merge its own permissions.allow and permissions.deny entries into ~/.claude/settings.json. TRIGGER when: user installed or upgraded the research plugin and its rules are not loading, or its deny rules are not blocking; phrases: 'set up research', 'research rules not loading', 'merge research permissions', 'after upgrading research'. SKIP: statusLine/TEAM_PROTOCOL/plugin-cache setup (use /f

Triggers from the description

set up researchresearch rules not loadingmerge research permissionsafter upgrading research

Arguments

/setup [--approve]
Original author description

Post-install setup for the research plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks and merge its own permissions.allow and permissions.deny entries into ~/.claude/settings.json. TRIGGER when: user installed or upgraded the research plugin and its rules are not loading, or its deny rules are not blocking; phrases: 'set up research', 'research rules not loading', 'merge research permissions', 'after upgrading research'. SKIP: statusLine/TEAM_PROTOCOL/plugin-cache setup (use /f

How it works

  1. Step 0: Flags
  2. Step 1: Python
  3. Step 2: Dry run — see what would change
  4. Step 3: Apply
  5. Step 4: Conflicts
  6. Step 5: Merge permissions.allow and permissions.deny
  7. Step 6: Report
Original SKILL.md headings · 147 lines, 1,394 words
SKILL.md preview
---
name: setup
description: "Post-install setup for the research plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks and merge its own permissions.allow and permissions.deny entries into ~/.claude/settings.json. TRIGGER when: user installed or upgraded the research plugin and its rules are not loading, or its deny rules are not blocking; phrases: 'set up research', 'research rules not loading', 'merge research permissions', 'after upgrading research'. SKIP: statusLine/TEAM_PROTOCOL/plugin-cache setup (use /foundry:setup (requires `foundry` plugin)); editing rule content (edit the plugin source)."
argument-hint: '[--approve]'
allowed-tools: Bash, AskUserQuestion
effort: low
---

<objective>

Deliver research's rules to Claude's user-level rule namespace, and its own permission rules to Claude's settings.

| Action | What happens |
| -- | -- |
| `rules/*.md` → `~/.claude/rules/research-<name>.md` | symlink |
| Stale link from an older research version | refreshed silently |
| Link whose source left the plugin | removed |
| Real file or foreign link at a destination | preserved, reported as conflict |
| Anything outside `~/.claude/rules/` | never touched |
| `.claude-plugin/permissions-{allow,deny}.json` → `~/.claude/settings.json` | merged additively except for the exact obsolete repository API rule |
| Any other key of `~/.claude/settings.json` | never touched |

**Why namespaced?** Claude loads user rules from one flat directory. Four plugins ship a `rules/quality-gates.md`; installing source basenames would collide. Every rule installs as `<plugin>-<source-name>.md`, so `quality-gates.md` becomes `research-quality-gates.md`. The prefix is inert — verified against Claude Code 2.1.220 that a filename prefix changes neither unconditional loading nor `paths:` frontmatter matching.

**Why symlink, not copy?** Rules load at session start. A symlink serves the installed version after every upgrade; a copy silently serves stale content forever.

**Why does research deliver only its own rules?** Each plugin installs independently. A plugin that shipped a sibling's rules would break standalone installation and couple releases. Still true with the delta variant: `research-quality-gates.md` links either `rules/quality-gates-delta.md` (when a foundry-owned `foundry-quality-gates.md` is already delivered) or the complete `rules/quality-gates.md` (when it is not) — both sources belong to this plugin, and the delta only *points* at foundry's copy for the shared obligations rather than delivering it. Standalone install loses no rule; all four `quality-gates.md` copies loading at once was 51,274 B of context on every turn.

NOT for: statusLine, `TEAM_PROTOCOL.md`, or plugin-cache purging — those are `/foundry:setup` (requires `foundry` plugin). Of `~/.claude/settings.json` only the `permissions.allow` and `permissions.deny` arrays are touched, additively except for removing the exact obsolete `Bash(gh api repos/*:*)` rule. Writes nothing under `~/.codex/`.

</objective>

<inputs>

- **No arguments** — interactive; prompts before replacing a conflicting destination.
- **`--approve`** — non-interactive; replaces conflicting destinations without asking. Used by `make sync-claude`.

</inputs>

<workflow>

## Step 0: Flags

Parse `$ARGUMENTS` for `--approve` (case-insensitive) → `APPROVE_ALL=true`, else `false`. Any other `--<token>` → print `` ! Unknown flag(s): `--<token>`. Supported: `--approve`. `` and stop.

## Step 1: Python

The probe runs at the head of the Step 2 block, in the same call: nothing is decided between them.

## Step 2: Dry run — see what would change

`$CLAUDE_PLUGIN_ROOT` is the installed plugin version. `sync_rules.py` re-validates it (manifest exists, parses, declares `research`; `rules/` is a real directory holding at least one non-empty regular `*.md`) and aborts before touching anything if any check fails.

```bash
# later steps run bare `python` (plugin bin/python shim on PATH) — probe that exact command
python --version 2>&1 | grep -qE "Python 3\.(1[0-9]|[2-9][0-9])" || { printf "! Python 3.10+ not found as 'python' — install it and re-run /research:setup\n"; exit 1; }
printf "  Python: %s\n" "$(python --version 2>&1)"
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}"
python "$PLUGIN_ROOT/bin/sync_rules.py" --plugin-name research --plugin-root "$PLUGIN_ROOT" --dry-run  # timeout: 15000
```

Non-zero exit → print stderr verbatim and stop; nothing was modified.

## Step 3: Apply

Run without `--dry-run`. `APPROVE_ALL=true` → run the `--approve` block below instead:

```bash
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}"
python "$PLUGIN_ROOT/bin/sync_rules.py" --plugin-name research --plugin-root "$PLUGIN_ROOT"  # timeout: 15000
```

`APPROVE_ALL=true` variant (also used when re-running after (b) in Step 4):

```bash
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}"
python "$PLUGIN_ROOT/bin/sync_rules.py" --plugin-name research --plugin-root "$PLUGIN_ROOT" --approve  # timeout: 15000
```

Output lines, one per destination: `linked:` · `unchanged:` · `replaced (--approve):` · `removed obsolete:` · `conflict, kept as-is:` · `FAILED:`.

Ownership is proved before any replace or remove: the existing link must resolve under the current plugin root, or under the same `~/.claude/plugins/cache/<marketplace>/research/` lineage as the current install. A link into another marketplace, another plugin, a source checkout, or a dotfiles tree is never adopted — path substrings are not evidence of ownership.

## Step 4: Conflicts

No `conflict, kept as-is:` lines → skip to Step 5.

`APPROVE_ALL=true` → conflicts were already replaced in Step 3; skip to Step 5.

Otherwise invoke `AskUserQuestion`, listing each conflicting destination and its current state:

- (a) **Keep them** — those rules stay undelivered
- (b) **Replace all with plugin links** ★ recommended — existing content is overwritten
- (c) **Abort** — leave everything as it is

On **(b)**, run the `--approve` block from Step 3 and report the resulting `replaced (--approve):` lines. On (a) or (c), report which rules remain undelivered.

## Step 5: Merge permissions.allow and permissions.deny

This plugin ships its own `permissions-allow.json` and `permissions-deny.json`. Claude Code does not read them from the plugin manifest, so without this step they are inert files — the allow entries never suppress a prompt and the deny entries never block anything.

Merge is idempotent: existing entries never duplicate. Each plugin merges only its own pair; the allow merge replaces the exact obsolete repository API rule and preserves every other entry.

The validation below uses Python’s standard JSON parser, so jq is not required. Create the file when this is a first install, and back it up before any write — a standalone install may reach this step with no `~/.claude/settings.json` at all:

```bash
export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
SETUP_BAK_TS=$(date -u +%Y-%m-%dT%H-%M-%SZ)
echo "$SETUP_BAK_TS" > "${TMPDIR:-/tmp}/research-setup-bak-ts-${CSID}"
[ -f ~/.claude/settings.json ] || printf '{}\n' > ~/.claude/settings.json  # created in-bash — no Write-tool prompt, headless-safe
cp ~/.claude/settings.json "$HOME/.claude/settings.json.bak-${SETUP_BAK_TS}"  # timeout: 5000
```

Report: "Backed up ~/.claude/settings.json → ~/.claude/settings.json.bak-<timestamp>"

Before merging, remove only the obsolete `Bash(gh api repos/*:*)` entry; nothing replaces it. Preserve the four broad allow entries already in settings, because foundry uses the same strings: `Bash(gh api repos/*)`, `Bash(gh api graphql:*)`, `Bash(git branch:*)`, and `Bash(git tag:*)`. Preserve every other user allow entry, all deny entries, and unrelated settings.

Writes merged `permissions.allow` and `permissions.deny` arrays via `merge_settings_permissions.py` — one atomic write covers both arrays, so allow never lands without deny. A missing or invalid shipped file aborts the block with settings unchanged. The same block then validates what was written: settings.json that no longer parses is restored from the backup taken above, the failure is printed, and the block exits 1 — report it and stop; zero exit → continue to Step 6:

```bash
export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}"
python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}/bin/merge_settings_permissions.py" --allow "$PLUGIN_ROOT/.claude-plugin/permissions-allow.json" --drop-allow 'Bash(gh api repos/*:*)' --drop-allow 'Bash(claude:*)' --drop-allow 'Bash(find:*)' --drop-allow 'Bash(node:*)' --drop-allow 'Bash(sed:*)' --drop-allow 'Bash(eval:*)' --deny "$PLUGIN_ROOT/.claude-plugin/permissions-deny.json" || { printf "! permissions merge failed — settings.json unchanged\n"; exit 1; }  # timeout: 5000
if ! python -m json.tool ~/.claude/settings.json > /dev/null; then  # timeout: 5000
    IFS= read -r SETUP_BAK_TS < "${TMPDIR:-/tmp}/research-setup-bak-ts-${CSID}" 2>/dev/null || SETUP_BAK_TS=$(ls -t "$HOME/.claude/settings.json.bak-"* 2>/dev/null | head -1 | sed 's/.*\.bak-//')
    cp "$HOME/.claude/settings.json.bak-${SETUP_BAK_TS}" ~/.claude/settings.json  # timeout: 5000
    printf "! settings.json failed validation after the merge — restored from %s\n" "$HOME/.claude/settings.json.bak-${SETUP_BAK_TS}"
    exit 1
fi
```

Writeback happens in-bash above (atomic rename). Report from the script's two output lines: "Added N new permissions.allow entries (M already present)." plus whether the exact obsolete repository API rule was removed (`dropped`), and "Added N new permissions.deny entries (M already present)." Also report: "stale gh deny entries from older versions: run /foundry:setup" (requires `foundry` plugin).

## Step 6: Report

- Rules linked: N → `~/.claude/rules/research-*.md`
- Unchanged: N · Obsolete removed: N · Conflicts kept: N (name each)
- Permissions: N allow entries added, N deny entries added
- Failures: N (name each; a failure means the platform refused the symlink — rules are never copied as a fallback)

</workflow>

<notes>

**Upgrade path**: `claude plugin install research@borda-ai-rig` then `/research:setup`. Links from the previous version share the install-cache lineage, so they refresh without prompting; a rule dropped in the new version has its link removed. `make sync-claude` runs `/research:setup --approve` headlessly for every installed managed plugin that ships a setup skill, so a normal sync needs no manual step.

**Uninstall leaves state behind**: Claude Code runs no cleanup hook on uninstall, and neither `claude plugin uninstall` nor `make clear-all` removes what setup created. After removing the plugin, delete `~/.claude/rules/research-*.md` by hand — they become dangling symlinks once the plugin cache version is gone.

**Testing**: setup is reachable only as `/research:setup` after the plugin is installed. To exercise it locally, bump `version` in `plugins/cc_research/.claude-plugin/plugin.json`, run `claude plugin install research@borda-ai-rig` from the repo root to refresh the cache, then invoke the skill. `bin/sync_rules.py` is a byte-identical propagated copy of the canonical helper; its regression suite lives beside that canonical copy in the AI-Rig repository.

**Follow-up gate omitted** — setup is one-shot; Step 6 is terminal output.

</notes>

Versions

RepositoryScoreLicence
This page · Borda/AI-Rig100Apache-2.0
HwangSlater/harness-fit100MIT
nesquikm/dev-process-toolkit100MIT
userKael/rastro100MIT
als-apg/osprey100BSD-3-Clause
dedujeong/gemba100Apache-2.0
eigenwise/eigenwise-toolshed100MIT
awrshift/agent-memory-kit100MIT
lifecycle-innovations-limited/claude-ops100MIT

Database snapshot: 13.11.2026 · package version b6420c71961c (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100permission-hygiene
    Diagnose and improve a Claude Code project's permission setup — the `.claude/settings.json` allow/ask/deny rules and the `.claude/settings.local.json` personal overrides. Use when settings.local.json has grown bloated (>20 rules, many one-shot), when permission prompts feel too…
  • 100settings-consolidator
    Scan every .claude/settings.local.json across the user's home directory, deduplicate permissions, collapse supersets, and merge into the global ~/.claude/settings.local.json with a categorized report. Also bootstraps permissions for autonomous/unattended sessions using a 350+…
  • 90deny-rules
    Sets up sensible permission deny rules in .claude/settings.json to block reads of .env and secrets, rm -rf, force pushes and production hosts, and explains each rule. Use when the user says lock down Claude, make Claude safer, protect my secrets, add deny rules, or stop Claude touching production.
  • 100koopa-claude-permissions
    Claude Code permission system internals, protected paths, permission modes, allow/ask/deny rule precedence, and the PreToolUse permissionDecision hook contract. Use when debugging unexpected permission prompts, understanding why Edit(.claude/**) or Bash(*) allow rules have no…
  • 100clean-permissions
    Clean permissions allow list in settings.json — removes one-off command pastes, entries redundant with broader wildcards, and dead MCP references. Use when user says \"clean permissions\", \"audit permissions\", \"clean up settings\", or \"prune allow list\".
  • 84audit-permission-state
    When the bundled fewer-permission-prompts skill resolves in this session, prefer it to reduce prompts via an allowlist; this skill to see the state in effect. Report-only: merges every settings scope into the allow/ask/deny set in effect with source and precedence per rule, and…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.