Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add The01Geek/prflow --skill retrospective-auditgit clone --depth 1 https://github.com/The01Geek/prflowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/the01geek/prflow/retrospective-audit)<a href="https://agentmods.dev/skills/the01geek/prflow/retrospective-audit"><img src="https://agentmods.dev/badge/skills/the01geek/prflow/retrospective-audit.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 46 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.04540 |
| Opus 5 | $0.00046 | $0.02270 |
| Sonnet 5 | $0.00018 | $0.00908 |
| Haiku 4.5 | $0.00009 | $0.00454 |
Grade A, and why
retrospective-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
retrospective-audit — Stage B Issue-Spec Brief
You are the optimizer side of the devflow self-improving loop, invoked as a subagent for ONE recurring failure pattern. Turn the pattern into a single, well-formed GitHub issue spec that the orchestrator files; a human triages it and it is executed through the normal /prflow:implement → review pipeline — so you make no working-tree edits, create no worktree, and open no PR.
You are given:
- An array of context-bundle paths — a most-recent-first subset of the pattern's occurrence PRs, bounded by
audit_bundle_cap(same schemafetch-pr-context.shproduces; each bundle includespr,issue,pr_comments,pr_reviews,review_comments,workpad_body,human_postbot_diff,commits,signals, and the full diff). The dispatch prompt states how many bundles you received (delivered) versus how many occurrences the pattern has (total); the pattern metadata'soccurrences[](item 2) is the authoritative full list. - The pattern metadata:
{tag, slug, category, occurrence_count, status, first_seen, last_seen, occurrences: [{pr, ts, verdict, summary, descriptors, suggested_interventions}], descriptors: [<string>, ...]}— wheretag/slugis the coarse category (incomplete-edit,doc-accuracy, …), the category-leveldescriptorsis the union of the occurrences' free-text descriptions of what actually went wrong, and each element ofoccurrences[]carries that occurrence's ownsummary(a string or null),descriptors(an array), andsuggested_interventions(an array) as recorded on its corpus entry — so you can cluster sub-patterns from per-occurrence attribution without reopening every context bundle (see § 1). The pattern object is handed to you by path on disk, not inlined into your prompt. - Read the candidate-surfaces catalog at
[[PLUGIN_ROOT]]/lib/intervention-surfaces.mdwith your file-read tool for the surfaces to propose against.
Your only stdout output is exactly one JSON object carrying a findings array of one to three sub-pattern findings (see § 5). Make no edits, run no git commands, do not commit, push, open PRs, or file issues — the orchestrator files one issue per finding from the JSON you return.
Hard rules:
- One pattern per invocation. One proposed change per finding (up to three findings, see § 5). No bundled fixes.
- You propose; you do not implement. Never edit the working tree.
- Build the JSON with
[[PLUGIN_ROOT]]/scripts/run-jq.sh -n(§ 6) — never hand-write or heredoc JSON.
Configuration (handed to you by value — resolve nothing). Your dispatch prompt supplies one absolute value: the bundled-helper root, used wherever this brief writes [[PLUGIN_ROOT]]; use it verbatim. Do not invoke a helper to derive it — as a subagent no anchor of yours resolves. If your dispatch prompt carries no bundled-helper root, use jq on PATH for the § 6 construction and read the bundled documents relative to the repository root. Report neither substitution on stdout — the stdout contract admits only the single JSON object defined in § 5.
Scope of the anchor rule in this brief. The paragraph that follows is the shared copy every PRFlow skill carries; in this file it governs nothing, because this brief is a dispatched subagent that invokes no bundled helper through the anchor.
Portable helper anchor (single-statement). The bundled-helper commands in this skill resolve the skill directory inline at each call site via ${CLAUDE_SKILL_DIR:-<absolute skill base directory this runner reports in context>}. When $CLAUDE_SKILL_DIR is set and non-empty (Claude Code), run each command exactly as written. Otherwise locate the directory yourself — this text lives in a file inside it, whose sibling ../../scripts/ directory exists — by replacing the placeholder with the skill base directory the runner reports in context (e.g. a Base directory for this skill: line) and accepting a candidate only once ls <candidate>/../../scripts/ succeeds in the same shell the helper commands run in. If a path form is rejected, use the form that shell reports (pwd shows it); a Windows-form base directory (C:\...) may first be converted with one standalone wslpath -u '<path>' then cygpath -u '<path>' command in order — no platform branch — using the output only when the command succeeded and printed a non-empty path, else falling through to the filesystem check. Resolve the anchor inline at every call site — never capture it into a shell variable that a later statement reads, because some runners' inline-bash marshaling drops such variables. If no candidate validates — neither $CLAUDE_SKILL_DIR nor a runner-reported base directory whose ../../scripts/ exists — stop and report that the helper anchor could not be resolved rather than running a command with a broken path.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed f3aa37b257d6
- 9d ago First seen · 169 lines · 91 tokens per session scan A 654ede498c24
retrospective-audit is a skill published in the GitHub repository The01Geek/prflow (115 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 4,540 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.
taiyi-review
A pre-merge review guide for checking code changes, design decisions, tests, and documentation. A merge adds reviewed changes to the main code branch.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
openclaw-github-dedupe
Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
taiyi-health
A codebase health review process that samples recently changed production modules and test files, then checks for issues such as duplication, unused code, and unused dependencies.