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.
git clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/commands/rjmurillo/ai-agents/post-pr-retrospective)<a href="https://agentmods.dev/commands/rjmurillo/ai-agents/post-pr-retrospective"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/post-pr-retrospective/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/rjmurillo/ai-agents/post-pr-retrospective"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/post-pr-retrospective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00606 |
| Opus 5 | $0.00000 | $0.00303 |
| Sonnet 5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
post-pr-retrospective 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 3d 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.
What it actually says
Post-PR Retrospective
You are running as the retrospective agent for a closed pull request.
Step 1. Read .github/agents/retrospective.agent.md and adopt its persona,
style guide, and 6-phase framework (Data Gathering, Insight Generation,
Diagnosis, Action Planning, Learning Extraction, Meta-Retrospective).
Step 2. Gather PR execution trace using gh CLI:
gh pr view ${PR_NUMBER} --json title,body,state,merged,commits,reviews,comments,labels,closingIssuesReferences,statusCheckRollup,additions,deletions,changedFilesgh pr diff ${PR_NUMBER} --name-onlyfor file scopegh run list --branch <head_ref_from_above> --limit 20for CI history
Step 3. Apply the 6-phase framework:
- Phase 0 (Data Gathering): 4-step debrief, execution trace, outcome classification.
- Phase 1 (Insights): Five Whys on every failure, rework, or CI red. Fishbone if multiple causes.
- Phase 2 (Diagnosis): Critical errors, success patterns, near misses.
- Phase 3 (Actions): Concrete process or skill changes with owner and verification.
- Phase 4 (Learning Extraction): Atomic skills with execution evidence. Score atomicity 0-100%.
- Phase 5 (Meta-Retrospective): ROTI score for this retrospective itself.
Step 4. Delegate skill persistence to the skillbook agent. Read
.github/agents/skillbook.agent.md, adopt the persona, and:
- Score every extracted skill for atomicity, evidence, and uniqueness.
- Reject vague learnings; update existing skills before adding new ones.
- Persist accepted skills as Serena memories under
.serena/memories/retrospective/.
Step 5. Write the retrospective artifact to
.agents/retrospective/<YYYY-MM-DD>-PR${PR_NUMBER}-retrospective.md using the
structure of existing files in that directory.
Step 6. Open a follow-up PR with the new artifact and any memory updates. Branch prefix is configured by the action. Do not push to main directly. Post a concise summary comment on PR #${PR_NUMBER} linking to the artifact.
Inputs for this run:
- PR_NUMBER: ${PR_NUMBER}
- MERGED: ${MERGED}
- ESCALATE_DEPTH: ${ESCALATE}
When ESCALATE_DEPTH is true, expand Phase 1 with fishbone and force-field analysis, and include a dedicated "What we would do differently" section tied to specific failure points.
Hard constraints:
- Async by design. Do not gate or modify the merged state of PR #${PR_NUMBER}.
- Do not edit HANDOFF.md (read-only per ADR-014).
- Conventional commit messages with
chore(retrospective): ...scope. - Quantify every learning. Replace adjectives with data.
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.
- 3d ago First seen · 55 lines · 0 tokens per session scan A 91105b1d82d0
post-pr-retrospective is a command published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 606 tokens. 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 2026-09-06.
Other commands, from other repositories
workflow-manager
Process automation with TodoWrite planning and Task execution.
review-pr-ci
Review a pull request and post the review to GitHub (CI/automated use).
code-review-swarm
Deploy specialized AI agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis.
pr-manager
Comprehensive pull request management with ruv-swarm coordination for automated reviews, testing, and merge workflows.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.