agentleFS
zyphr-labszyphr-labs/bounty-harness/.claude/skills/enrichment/SKILL.md

enrichment

Skill1 starsChanged 3 months agoMITView on GitHub

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Start with enrich to run a post-script on the next unenriched finding.

    line 14
  2. Very specific:

    Use supplemental to re-run a different post-script on previously enriched findings (additive, history preserved).

    line 15
  3. Very specific:

    Use list-enrichments to inspect existing enrichments without running anything.

    line 16
  4. Very specific:

    Keep post_script name, prompt template, and output JSON in $OUTDIR/enrichment/enrichments.jsonl (and .bb/enrichments.jsonl if you use that …

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Enrichment

Overview

Post-processing that enriches verified findings with report drafts, proof-of-concept diffs, and triage chips. Inspired by Kritt's post-scripts: each enrichment is a focused prompt that receives a single finding's context (vulnerability fields, trigger flow, file path) plus scan context, and produces typed output that is stored separately from the finding itself.

Quick Reference

  • Skill: enrichment
  • Severity range: info, low, medium, high, critical
  • Required tools: python3, jq
  • Expected input files: output/*/impact-verifier/verified.jsonl or reports/ranked.jsonl
  • Scope check: passive enrichment (local file transformation, no network unless --llm is set).

Workflow Selection

  • Start with enrich to run a post-script on the next unenriched finding.
  • Use supplemental to re-run a different post-script on previously enriched findings (additive, history preserved).
  • Use list-enrichments to inspect existing enrichments without running anything.
  • Runbooks: runbooks/ and select the closest phase when workflow names do not map 1:1.

Available Workflows

WorkflowPurposeScript pathsPrimary outputsEvidence
enrichRun a post-script on the next unenriched finding.claude/skills/enrichment/scripts/enrich.py$OUTDIR/enrichment/enrichments.jsonl$OUTDIR/enrichment/evidence/
supplementalRe-run a post-script on a previously enriched finding (additive).claude/skills/enrichment/scripts/enrich.py$OUTDIR/enrichment/enrichments.jsonl$OUTDIR/enrichment/evidence/
list-enrichmentsList enrichments and their status.claude/skills/enrichment/scripts/list_enrichments.pystdout—

Evidence Required

  • Store the finding's original bounty_rank and vulnerability_type alongside the enrichment
  • Keep post_script name, prompt template, and output JSON in $OUTDIR/enrichment/enrichments.jsonl (and .bb/enrichments.jsonl if you use that path via symlink)
  • _reserved_report output is markdown for the report tab; _reserved_poc is a git diff for the PoC tab; _chip_* outputs are short tags aggregated from all enrichments
  • Redact tokens and PII before sharing enrichments; evidence stays local-only

References

  • Source of truth: skill.yaml
  • Runbooks: runbooks/
  • Kritt post-scripts: open-kritt docs-site/post-scripts/*.mdx (reserved keys, supplemental runs)

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.