agentleFS
tanishq286tanishq286/tq-forge/skills/tq-forge-status/SKILL.md

tq-forge-status

Skill8 starsChanged 5 months agoMITView on GitHub

Show the forge state at a glance: how many skills/agents are forged, what's in the queue, what needs manual review, and whether the halt flag is set. Use when asked for "/tq-forge-status", "forge status", "what's queued", or "where's the forge at".

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All clear -> suggest /tq-forge "<intent>" to forge new work

    line 65
  2. Distinctive:

    All subcommands should exit 0.

    line 71

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/tq-forge-status — forge state snapshot

When to use

A quick "where am I" check. Three questions in one place: what have I forged, what's queued, and is forge currently paused?

Procedure

export TQ_FORGE_HOME="${TQ_FORGE_HOME:-$HOME/.tq-forge}"
S="${CLAUDE_PLUGIN_ROOT:-${TQ_FORGE_HOME:-$HOME/.tq-forge}/install}/scripts"
source "$S/common.sh" && tq_ensure_home
  1. Inventory counts.
    python3 -c "import json,pathlib,os;d=json.loads((pathlib.Path(os.environ['TQ_FORGE_HOME'])/'skill-log.json').read_text() or '[]');import collections;c=collections.Counter(e.get('status','?') for e in d);print('total',len(d),dict(c))"
  2. Queue depth.
    bash "$S/forge-checkpoint.sh" status
  3. Halt status.
    test -f "$TQ_FORGE_HOME/halt.flag" && echo "⏸  HALT ACTIVE — $(cat "$TQ_FORGE_HOME/halt.flag")" || echo "▶  no halt"
  4. Last forged item.
    python3 -c "import json,pathlib,os;d=json.loads((pathlib.Path(os.environ['TQ_FORGE_HOME'])/'skill-log.json').read_text() or '[]');e=d[-1] if d else None;print('last:',e['slug'],e.get('kind'),'score',e.get('score'),e.get('at')) if e else print('last: (none yet)')"
  5. Render a single combined panel:
    ═══════════════════════════════════════════════════
     tq-forge — Status
    ═══════════════════════════════════════════════════
     Forged:   <T> total   (<S> sandbox · <P> promoted · <R> needs review)
     Queue:    <Q> pending intents
     Halt:     <yes/no>
    ───────────────────────────────────────────────────
     Last forged:  <slug>  <kind>  score=<S>  <ago>
    ═══════════════════════════════════════════════════
  6. Suggest the next action by state:
    • Queue >= 1 + no halt -> /tq-forge-resume to drain it
    • Halt active -> "Remove $TQ_FORGE_HOME/halt.flag to resume."
    • Items in needs_manual_review -> /tq-forge-queue
    • All clear -> suggest /tq-forge "<intent>" to forge new work

Pitfalls

  • The "last forged" line reads skill-log.json. If you've never run /tq-forge, it's an empty array — show "(none yet)" rather than erroring.
  • All subcommands should exit 0. If one fails, print the failing one and continue — a partial status beats no status.

Verification

  • The status panel renders without a Python traceback.
  • The counts shown match skill-log.json and forge-queue.json.

Tags

tq-forge status read-only

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.