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 XRenSiu/claude-code-forge --skill retrogit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/xrensiu/claude-code-forge/retro)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/retro"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/retro.svg" alt="Measured on agentmods" 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 | $0.00241 | $0.02054 |
| Opus 5 | $0.00120 | $0.01027 |
| Sonnet 5 | $0.00048 | $0.00411 |
| Haiku 4.5 | $0.00024 | $0.00205 |
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 today.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
retro — 先测基线，再看病在哪层
产物：retro/retro-<date>.md（基线表 + 发现 + 提案，形状 assets/retro_template.md）与 metrics.json。
本文件写：度量在流水线里是什么、什么算一条有用的发现、原语与出口、提案的去向。怎么解读是你的份额，
但每条提案必须有去向和验收方式。
缺口（Knowledge + Judgment + Capability）
deletion 测试：撤掉本 skill，引擎会写"这次沟通不够充分，下次加强测试"——没有数字、没有层、没人能验收。 缺的是：数据在哪（Σ）、什么算流程病的信号（φ）、导出脚本（Π）、提案必须落到层（γ）。
世界（Σ）
-
数据全部来自归档，不需要额外埋点：
specs/<slug>/state.json（阶段时间戳、分层计数、门的裁决、豁免）、ledger.md（每次失败与路由）、done_when.yaml（human AC 占比）、escape-defects.md、releases/*.md、.sdlc/pr-watch/*.json（review 轮次与 verdict 分布）。 -
指标与它诊断的层：
指标 数据源 高了说明哪层病 回流分布（card/plan/task/ontology/world） counters 哪一层最常被退回 = 那层的门太松或上游没建好 门的拦截次数 G1/G2/G3 ledger.md的 gate 行（缺则 trace.jsonlkind=gate）高 = 推导常错（PSL 欠定）或世界常错（好事：拦住了）。不读 state.json#gates.*.verdict：那是最终态，拒两次再过的运行在那里读出来是 0 次拦截（I-84）。归档既无账本也无 trace 时才退回最终态，此时gate_source记为state(final-verdict-only)human AC 占比 done_when 持续过半 = 该类需求不该走流水线 PR 返工轮次 review.rounds / pr-watch 高 = 契约或卡的粒度问题，不是 reviewer 苛刻 逃逸缺陷率 escape-defects 压住"切小任务刷首过率"；逐条看归因层 豁免数 waivers 门被 --force 绕过的次数；> 0 就要问为什么 按体量分桶的逃逸缺陷率（v0.4） state.intake.size + escape-defects S 档豁免了整体验收，它的逃逸率如果不低于 M，说明分档标准定错了——分档对不对由逃逸缺陷回答，不由拍脑袋回答 size_exemption 次数（v0.4） ledger 的 size_exemption 行 每一次都是一次"这次不跑六审"的决定；数它，别让它变成默认 agent-map 候选（v0.4） ledger 的失败指纹 + 逃逸缺陷 同一个坑绊倒第二个实现者 = 它该进 agent-map.md的「已知陷阱」并带上这条 ledger 行做来路lead time created_at → merged_at 与轮次一起看，单看无意义 逃逸缺陷因果链（v0.6） trace.jsonl：escape → caused_by* → 根 深度与根的层直接回答"为什么门没拦住"；根在 task = 契约；根在 gate = 人签时没看到 契约返工率（v0.6） trace.jsonl： supersedes done_when.yaml#AC-*/ AC 总数高 = G2 之前判据写得太早或太松 -
基线先于结论：第一次跑只记基线（带日期），不下诊断；第二次起比差值。
-
提案的去向是封闭集：
psl（改规律 / 补 Mental Model）、dos（本体修订 → 变更提案）、invariant（→ /invariant-extract）、ac（收紧 done_when → 变更提案）、routing（预算 / 指纹阈值）、skill（某 skill 的 fix_list）、human（需要人定）。 -
关于用户的 Σ："复盘一下"= 要数字 + 提案，不要感想；"这次做得挺好"= 也记基线。
What ships with it
12 files 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.
- assets/retro_template.md 811 B
- eval/fixtures/feat-a/done_when.yaml 1.4 KB
- eval/fixtures/feat-a/escape-defects.md 201 B
- eval/fixtures/feat-a/state.json 573 B
- eval/fixtures/feat-a/trace.jsonl 3.2 KB
- eval/fixtures/feat-b/ledger.md 1.3 KB
- eval/fixtures/feat-b/state.json 607 B
- eval/fixtures/feat-c/state.json 611 B
- eval/gate.json 1.4 KB
- eval/report.md 734 B
- references/reading-the-numbers.md 1.6 KB
- scripts/metrics.py 14 KB runs code
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.
- today Changed · +5 lines cbf9f7c6208a
- yesterday First seen · 82 lines · 241 tokens per session scan A 7e725ff41cf6
retro is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed today), licensed MIT. It adds 241 tokens to every session and 2,054 once invoked, about $0.0012 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 2026-09-05.
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…
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…