Borrowing it
Nothing to install: this file belongs to open-software-network/os-clovy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/open-software-network/os-clovy/main/.agents/skills/repo-retrospect/SKILL.mdgit clone --depth 1 https://github.com/open-software-network/os-clovyWrote 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/open-software-network/os-clovy/repo-retrospect)<a href="https://agentmods.dev/skills/open-software-network/os-clovy/repo-retrospect"><img src="https://agentmods.dev/badge/skills/open-software-network/os-clovy/repo-retrospect/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/skills/open-software-network/os-clovy/repo-retrospect"><img src="https://agentmods.dev/badge/skills/open-software-network/os-clovy/repo-retrospect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00123 | $0.01191 |
| Opus 5 | $0.00062 | $0.00596 |
| Sonnet 5 | $0.00025 | $0.00238 |
| Haiku 4.5 | $0.00012 | $0.00119 |
Grade A, and why
repo-retrospect 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 10d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo retrospect
Turn a finished build cycle into pipeline improvements. The premise: every cycle produces calibration data — what the local battery missed, what external reviewers caught, where the orchestrator mis-triaged, what the user had to correct — and that data is worthless unless it lands in the file the next cycle actually reads. This skill is the loop that closes the loop.
Run it at the end of a cycle: after the PR merges, after the review loop is closed out, or whenever the user asks what the pipeline should learn.
1. Gather evidence (three sources, all of them)
- The session conversation — the orchestrator's own history: triage decisions and which later proved wrong (a "no change needed" that a later round reopened), permission blocks and the fallbacks used, tool/environment failures (ports, agents, signing), plan assumptions the code contradicted, and anything the docs-grill found stale.
- PR review surfaces — all three, via
gh(same discipline as the repo-build-pr review loop): inline threads with their reply chains (gh api .../pulls/<n>/comments), review bodies (gh pr view <n> --json reviews— collapsed<details>tables included), and summary comments. For each finding record: who found it, which round, the disposition, and — the key question — why the local battery did not find it first. - User feedback — explicit corrections, clarifying-question answers that overrode a default, mid-build scope changes, and anything the user flagged after the fact. User corrections outrank model judgment: a lesson the user taught twice is a rule, not a note.
2. Classify each lesson to its single owner
Each fact lives in exactly one file (the skill-map convention). Route:
| Lesson shape | Owner |
|---|---|
| Reviewer precision/recall fact, per-bot behavior, round counts | repo-review/CALIBRATION.md (one row per reviewer per cycle) |
| Systematic review blind spot (a failure class, seen once with evidence) | repo-review/axes/<axis>.md — extend a lens, never bolt on a new section when an existing one fits |
| Battery sizing, convergence, or dispatch lesson | repo-review/SKILL.md |
| Build-workflow order, chunking, validation, or publish lesson | repo-build-pr/SKILL.md |
| Brief-writing or delegate-verification lesson | repo-delegate/SKILL.md |
| Walkthrough/QA technique gotcha | browser-test-tauri-fe or agent-e2e-qa |
| Domain term sharpened or invented mid-cycle | CONTEXT.md (same-change rule) |
| Hard-to-reverse decision with a real trade-off | new ADR (append-only; AGENTS.md three-part test) |
| Cross-skill convention change | AGENTS.md or docs/agents/collaboration.md |
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.
- 10d ago First seen · 90 lines · 123 tokens per session scan A a0d1e709dedb
repo-retrospect is a skill published in the GitHub repository open-software-network/os-clovy (356 stars, last pushed today), licensed MIT. It adds 123 tokens to every session and 1,191 once invoked, about $0.0006 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
personal-commands
Edit hex.config.ts, not .hex-sdk. Config and installed dependencies execute with the user's normal permissions; use only trusted packages and avoid network, filesystem, environment, or subprocess access unless the requested command requires it. Run bun run check after editing.
hex-personal-commands
Configure HEX personal voice commands, voice-dictation control phrases, and deterministic transcript transformations. Use when the user wants to add or change commands or transformations for the HEX macOS voice app.
macparakeet-stt
Use when the user asks to transcribe audio or video, search MacParakeet's local speech library, retrieve cited transcript segments or knowledge cards, or inspect and manage saved meeting artifacts on macOS Apple Silicon.
murmur-mcp
Query Murmur's local read-only MCP server for gated, indexed knowledge — semantic + full-text search over meetings and notes, entity dossiers, structured transcripts, open-commitment rollups, and typed note-folder database queries. Prefer this over grepping raw vault files. Use when you need to find, retrieve, or…
murmur-vault
How to coexist with Murmur's notes in an Obsidian vault — note anatomy, front-matter keys, managed sections you must never edit, wikilink discipline, entity stubs, where files live, the locked-folder disappeared-file rule, and the add-freely/prefer-append coexistence contract. Use when reading, editing, or creating…
frame-macos-notification
Realistic macOS notification banner with app icon, title, and body, suited to video overlays or product teasers.