Skip to content
Skills Library
AI & agents · Analysis

status

/status

Show a provider-neutral, freshness-aware snapshot of active Agent work, Git delivery, execution identity, and usage limits. Use for “what's going on right now”, what is running, progress updates, active runtime/provider/model, or stuck-work checks.

Repository
clade ↗
Licence
MIT
Last repository change
24.10.2026

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
5
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 24.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Show a provider-neutral, freshness-aware snapshot of active Agent work, Git delivery, execution identity, and usage limits. Use for “what's going on right now”, what is running, progress updates, active runtime/provider/model, or stuck-work checks.

Triggers from the description

what
Original author description

Show a provider-neutral, freshness-aware snapshot of active Agent work, Git delivery, execution identity, and usage limits. Use for “what's going on right now”, what is running, progress updates, active runtime/provider/model, or stuck-work checks.

How it works

  1. Canonical Clade workflow
  2. Required semantic fields
  3. Collection order
  4. Output
  5. Completion
  6. Codex surface adapter
  7. Additional skill reference
  8. Delivery completion
Original SKILL.md headings · 129 lines, 734 words
SKILL.md preview
---
name: status
description: "Show a provider-neutral, freshness-aware snapshot of active Agent work, Git delivery, execution identity, and usage limits. Use for “what's going on right now”, what is running, progress updates, active runtime/provider/model, or stuck-work checks."
---

# Clade for Codex

This package composes the provider-neutral Clade core contract with the native
Codex surface adapter. Run the workflow directly in Codex; do not launch
another agent CLI or route it through Clade MCP.

Package provenance:

- core contract: `clade.status/v1`
- surface adapter: `codex/v1`
- explicit invocation: `$clade:status`
- generated from: `configs/skills/<name>`

## Canonical Clade workflow

<command-metadata>
name: status
contract: clade.status/v1
completion-status: DONE | DONE_WITH_CONCERNS | BLOCKED
</command-metadata>

Build one compact status snapshot from sources available on the current
surface. Keep collection read-only.

## Required semantic fields

- `observed_at`
- task identity/state and progress `{completed,total,source}`
- Git branch, dirty state, checkpoint SHA, upstream divergence
- execution runtime, connection, inference provider, wire model, degradations
- usage/rate-limit observations with source and observed/reset timestamps
- freshness per source

Unknown is a first-class value:

- Never render missing progress or quota data as `0`, `0%`, unlimited, or done.
- Never infer a provider from a model prefix or a model from the runtime name.
- Mark estimates explicitly and show the evidence behind them.
- Distinguish stale data, unreachable sources, unsupported capabilities, and
  authoritative zero values.

## Collection order

1. Read conversation/runtime activity exposed by this surface.
2. Inspect local Git without mutation. Prefer the delivery controller's
   `git_context.py` when installed; otherwise use read-only Git commands.
   When the Git-common `clade/tasks/binding.json` exists, resolve the installed
   tasks skill directory as TASKS_ROOT and run
   `python3 "$TASKS_ROOT/scripts/maintenance.py" status` first. This reads
   maintenance observations without requiring the database, and reports stale
   health, missing/failed backups and restore verification. Treat an unmanaged
   or unsupported service as unknown, not healthy. Then run
   `python3 "$TASKS_ROOT/scripts/tasks.py" snapshot`. Use its project/task/
   session IDs, ownership, ready set and submission evidence. An unavailable
   backend is unavailable, not zero tasks. Do not run claim or heartbeat here.
3. Read Clade worker `status_snapshot` / `execution_envelope` if an
   orchestrator is reachable.
4. Query forge/CI only when a related PR is in scope.
5. Query native usage data only through the current surface adapter.

## Output

Keep the human view under 20 lines unless the user asks for JSON. Show:

```text
Work:       state · factual progress or unknown · freshness
Git:        branch · dirty/clean/unknown · checkpoint/upstream
Execution:  runtime · connection · inference provider · wire model
Limits:     authoritative windows, or unknown/unavailable with reason
Delivery:   PR/checks/merge state when in scope
Concern:    stale/hung/degraded evidence, if any
Next:       one concrete recommendation
```

Call work “hung” only when a source provides timestamps and no relevant change
has occurred past the repository/runtime threshold. Do not kill, restart,
commit, push, or merge from this read-only skill.

## Completion

- `DONE`: snapshot is clear and all relevant sources were observed.
- `DONE_WITH_CONCERNS`: one or more sources are stale, unavailable, or
  degraded; name them.
- `BLOCKED`: even local/runtime state cannot be read; show the exact failure.

## Codex surface adapter

# Codex status adapter

- Invoke the installed plugin workflow explicitly as `$clade:status`; bare
  `$status` is not the Clade plugin identity.
- Use Codex task/tool activity exposed in the current conversation.
- Codex TUI status-line configuration is an ordered list of native fields, not
  an arbitrary command renderer. Do not claim Claude-style custom rendering.
- Use `$clade:codex-usage --json` when installed for authenticated native limit
  observations; otherwise report limits as unavailable/unknown.
- Read the applicable agent instructions before interpreting
  repository-specific progress. `AGENTS.override.md` wins over `AGENTS.md` at
  each scope with no merge, so do not report a shadowed `AGENTS.md` as in
  effect; trusted legacy `CLAUDE.md` is Clade's own fallback rather than a
  filename Codex resolves.
- Do not launch a nested Codex CLI to discover status.

## Additional skill reference

# Status

Render one `clade.status/v1` snapshot. Separate observed facts from estimates,
attach source/freshness, and preserve unknown values as unknown. Read
`prompt.md` for the core contract and only the current runtime file under
`surfaces/` for collection mechanics.

## Delivery completion

If this workflow changes files or external state:

- Inspect the real final state before responding, including `git status` for a
  repository task.
- Never report `DONE` while task-owned changes are uncommitted. Use or continue
  `$clade:delivery` and create a repository-compliant checkpoint or preserve
  the work when committing is unavailable.
- When the user request or trusted repository policy makes publication,
  deployment, or live verification part of the task, do not silently downgrade
  the result to local-only work.
- If a required delivery transition lacks authority, credentials, a destination,
  or reachable external state, report `BLOCKED` or `NEEDS_CONTEXT` rather than
  appending a "not committed/pushed/deployed" caveat after `DONE`.
Files in this package (5)
  • SKILL.md 6 KB
  • surfaces/claude-code.md 1 KB
  • surfaces/codex.md 1 KB
  • surfaces/generic.md 1 KB
  • surfaces/mcp.md 1 KB

Versions

RepositoryScoreLicence
This page · shenxingy/clade100MIT
finolabs/finolabs-vibecode100MIT
jeremylongshore/tons-of-skills-marketplace100MIT
rossoctl/context-guru100Apache-2.0
crisandrews/clawcode100MIT
wrg32786/aigent-os100MIT
zereight/gitlab-mcp100MIT
emaballarin/ccplugins100MIT
wookiya1364/scv-claude-code100MIT

Database snapshot: 13.11.2026 · package version 3e580c5e251b (SHA-256 digest of the entire package)

Downloads in the last 30 days: 1 · ranking

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

Similar skills

  • 95ar-status
    Show experiment dashboard with results, active loops, and progress. Use when the user runs /ar:ar-status or asks how an autoresearch experiment is going.
  • 90live
    Use when the user asks about running sessions, agent status, what needs attention — e.g. 'what's running', 'live status', 'which sessions need me', 'agent status', 'check on my agents', 'are my sessions done', 'anything stuck
  • 90ralph-specum-status
    This skill should be used only when the user explicitly asks to use `$ralph-specum-status`, or explicitly asks Ralph Specum in Codex for status or active spec progress.
  • 100use-claude-limits-efficiently
    Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.
  • 100usage-bridge
    Use when the user runs /galdr:usage-bridge to install, remove, or check galdr's statusline rate-limits bridge on this machine — the wrapper that makes the usage % and quota-park work. Run install once per machine; uninstall to fully revert; status to check.
  • 100bernstein-status
    Show Bernstein orchestrator status - active agents, task progress, costs, and alerts. Use when the user asks about orchestrator status, what agents are doing, task progress, how much has been spent, or what's happening with the build.

Feedback and reports

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