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 uxname/LiteStack --skill retrogit clone --depth 1 https://github.com/uxname/LiteStackWrote 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/uxname/litestack/retro)<a href="https://agentmods.dev/skills/uxname/litestack/retro"><img src="https://agentmods.dev/badge/skills/uxname/litestack/retro/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/uxname/litestack/retro"><img src="https://agentmods.dev/badge/skills/uxname/litestack/retro.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 | $0.00065 | $0.01002 |
| Opus 5.5 | $0.00026 | $0.00401 |
| Sonnet 5.5 | $0.00013 | $0.00200 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
retro 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 11d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A retro exists for prevention: the next agent reads docs/retro/ before touching code
(root AGENTS.md, step 1), so every lesson must change what that agent does. The strongest
prevention is a check — a gate goes red on the mistake whether or not anyone read the
lesson. A written rule covers what no tool can see.
Step 1: List what went wrong
Mine the session for mistakes, dead ends and wrong assumptions:
- commands and tests that failed (quote the error);
- wrong files edited, paths that did not exist, the wrong submodule touched;
- a convention misread (wrong Biome quote style,
lintrun instead ofnpm run check,--no-verify); - a fix that was redone, reverted, or broke something else;
- time lost to a wrong model of how the code works.
Done when every such event of the session is on the list with its evidence. An empty list means the session was clean: tell the user so and stop — a retro without a problem is noise.
Step 2: Classify each problem — check or rule
- Mechanical — a fixed pattern a tool can see: a banned API or import, a file in the
wrong place, a stale generated file, a skipped command. Its prevention is a check: a
linter rule (golangci-lint, go-arch-lint, Biome, steiger), a lefthook command, or a test.
Start from the gates that already run (
docs/TEAM.md→ "Quality gates"): a check that exists but is unwired, skipped or silently green is the finding itself, and the fix is to repair it. - Judgement call — needs context to see: the wrong layer, code that clashes with its
surroundings, a misread requirement. Its prevention is a rule. A rule that should
bind all future work, beyond warning about this one trap, belongs in the owning
CODING_STANDARDS.mdor.agents/*.md— propose moving it there.
Done when every problem carries one label and a concretely named prevention.
Step 3: Write the file
Pick area: backend, frontend, meta, or cross (both submodules or the seam
between them). Take the date from date +%F. Filename:
docs/retro/<YYYY-MM-DD>-<short-slug>.md, slug = session topic in kebab-case; if today's
file for this topic exists, append to it.
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.
- 11d ago Changed · +15 lines · -14 tokens per session 8639fe43f198
- 14d ago Changed · +1 tokens per session 8bee81d3d1b7
- 1mo ago First seen · 59 lines · 78 tokens per session scan A 2e2670bbfaac
retro is a skill published in the GitHub repository uxname/LiteStack (2 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 1,002 once invoked, about $0.0003 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…