agentsclimarketplace

Loopify trace

Skill AndreRatzenberger/loopify/plugins/loopify/skills/loopify-trace

Loop yes. Prompt no. Agent skills that turn specs into checked agent loops with receipts.

Install
npx -y skills add AndreRatzenberger/loopify --skill loopify-trace

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when creating, maintaining, auditing, or summarizing loop trace receipts that record checks, failures, patches, rationale, evidence, and stop reasons.

SKILL.md

1.5 KB, as published. Nobody here has run it

loopify-trace

Maintain loop receipts.

When To Use

  • A loop needs a trace file.
  • A finished loop needs evidence summarized.
  • The user asks what happened across attempts.
  • A trace is messy, missing turn data, or missing a stop reason.

Do Not Use

  • Do not rewrite failed attempts out of the trace.
  • Do not present a passing command as broader proof than it is.
  • Do not hide missing evidence.

Workflow

  1. Locate the loop directory or named trace file.
  2. Create trace.md from templates/trace.md if missing.
  3. Record each turn with command, result, failure, patch, rationale, and next check.
  4. Preserve failed attempts and rejected directions.
  5. Summarize final stop reason and evidence.
  6. Use templates/final-evidence-summary.md for completion summaries.
  7. Update .loopify/index.md when the stop reason changes.
  8. Run the trace checker if available.

Output

Default output: .loopify/loops/NNN-slug/trace.md, plus a final evidence summary when requested.

Legacy runs/trace.md paths are supported when the user names one.

Validation

  • A reader can reconstruct the loop from the trace.
  • Every final claim points to evidence.
  • Missing trace data is flagged.

Example

Use loopify-trace to summarize .loopify/loops/001-papertrail/trace.md and report the stop reason plus residual risk.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.