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 MotWakorb/ai-agent-dev-team --skill retro-minegit clone --depth 1 https://github.com/MotWakorb/ai-agent-dev-teamWrote 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/motwakorb/ai-agent-dev-team/retro-mine)<a href="https://agentmods.dev/skills/motwakorb/ai-agent-dev-team/retro-mine"><img src="https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/retro-mine/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/motwakorb/ai-agent-dev-team/retro-mine"><img src="https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/retro-mine.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 | $0.00060 | $0.00892 |
| Opus 5 | $0.00030 | $0.00446 |
| Sonnet 5 | $0.00012 | $0.00178 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
retro-mine 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 9d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retro Mine
Turn the retro corpus into actionable changes to this skill system. This formalizes the "retro-driven rule additions" passes previously done by hand (see CHANGELOG). Run it from the ai-agent-dev-team repo — the output targets its skill files.
Retros are the stress test for skill rules: patterns found here become rules, and future retros validate them. Both directions matter — new patterns need new rules, and recurring patterns that already have rules mean the rule isn't working.
Process
-
Pull — gather everyone's latest retros (
/retro-syncis push-only):git -C ~/retros pull --rebase origin mainIf
~/retrosisn't a git repo yet, run/retro-synconce to bootstrap it, then pull. -
Watermark —
retro-mine/LAST_MINEDin this repo holds the filename of the newest retro covered by the last pass. Retro filenames are date-prefixed, so "new" = every date-prefixed file (~/retros/20*.md) sorting after it — ignore the corpus README. Missing watermark = mine the whole corpus. -
Extract — spawn reader agents (
persona-reviewer,model: sonnet), ~5 retros per agent. Each returns, per retro, only what's structurally reusable:- Agent failure modes (what the agent got wrong, and at what point in the session)
- PO friction (what made the work harder — process, not personality)
- Process/skill gaps (Section 5 and persona "What I'd flag" entries)
- Keep / Stop / Start lessons
- For each: a one-line candidate rule and the skill file that would own it
Readers quote the retro (filename + line) as evidence — no paraphrase-only findings.
-
Cluster (orchestrator) — group findings across retros by failure family and owning file:
- ≥2 retros showing the same pattern → rule candidate
- 1 retro → watch item; record it, don't propose a rule yet
- Pattern already covered by an existing rule → check the rule's landing date (
git logon the owning file). Recurrences in retros dated after the rule landed are a rule-not-working signal — propose strengthening or enforcement (hook), not a duplicate rule
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 53 lines · 60 tokens per session scan A b8d17b8282b9
retro-mine is a skill published in the GitHub repository MotWakorb/ai-agent-dev-team (2 stars, last pushed 27d ago), licensed MIT. It adds 60 tokens to every session and 892 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…