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

tq-forge-resume

Skill8 starsChanged 5 months agoMITView on GitHub

Resume forge work after a pause: clear the halt flag (with confirmation) and drain any queued intents. Use when asked for "/tq-forge-resume", "resume forge", "process the forge queue", or "unpause the forge".

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are 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.

  • 2

    Very specific

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

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

    Drain the queue: If queue is non-empty, list each intent and ask "Process the queue now?" via AskUserQuestion.

    line 45
  2. Distinctive:

    Don't clear the halt flag silently.

    line 65
  3. Very specific:

    If a previous session left a partial sandbox artifact (truncated SKILL.md), delete it and re-forge fresh rather than trying to patch it.

    line 67

≈ “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-resume — pick up where you left off

When to use

Either:

  1. You paused forge work with $TQ_FORGE_HOME/halt.flag and want to clear it.
  2. Intents piled up in the queue while forge was paused and you want to drain them now.

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. Inspect current state.
    bash "$S/forge-checkpoint.sh" status
    test -f "$TQ_FORGE_HOME/halt.flag" && echo "⏸  halt set: $(cat "$TQ_FORGE_HOME/halt.flag")" || echo "▶  no halt"
  2. If the halt flag is set, ask the user via AskUserQuestion: "Clear the halt flag and resume?" Options: "Clear and resume", "Keep paused".
    • On "Clear and resume":
      rm -f "$TQ_FORGE_HOME/halt.flag"
      echo "▶  Resumed."
  3. Drain the queue. If queue is non-empty, list each intent and ask "Process the queue now?" via AskUserQuestion. On yes, loop:
    while INTENT="$(bash "$S/forge-checkpoint.sh" pop)"; [ -n "$INTENT" ]; do
      test -f "$TQ_FORGE_HOME/halt.flag" && echo "⏸  halt re-set — stopping." && break
      echo "Processing: $INTENT"   # then follow the /tq-forge procedure for each
    done
    For each popped intent, run the full /tq-forge flow (classify -> scaffold -> score -> log).
  4. On completion, print what was processed and the remaining queue depth:
    bash "$S/forge-checkpoint.sh" status
  5. If nothing is pending, print 🎉 Nothing queued — forge is up to date.

Pitfalls

  • Don't clear the halt flag silently. Always confirm — the flag exists precisely to make a deliberate pause deliberate to undo.
  • If a previous session left a partial sandbox artifact (truncated SKILL.md), delete it and re-forge fresh rather than trying to patch it.
  • Re-check the halt flag inside the drain loop. A long batch can trip a new pause; honor it.

Verification

  • forge-checkpoint.sh status shows 0 pending after a full drain.
  • $TQ_FORGE_HOME/halt.flag no longer exists if the user chose to resume.
  • Each processed intent produced a new entry in skill-log.json.

Tags

tq-forge resume queue

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.