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 implementgit 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/implement)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/implement"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/implement.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 | $0.00216 | $0.01925 |
| Opus 5 | $0.00108 | $0.00962 |
| Sonnet 5 | $0.00043 | $0.00385 |
| Haiku 4.5 | $0.00022 | $0.00193 |
Grade A, and why
implement 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
implement — 一张卡,一个看不见评审的实现者
产物是限定在卡白名单内的 diff、按 /commit 规则落地的 commit(footer Card: CARD-xx)、以及状态机里
该卡的 done 状态。本文件写:实现者能看到什么、什么算做完、原语与门、失败怎么走。怎么写代码是引擎的份额。
缺口(Control + Judgment)
deletion 测试:撤掉本 skill,引擎会把整个对话历史、评审 skill 的判据、其他卡的改动一起塞给实现者,
改动溢出白名单、顺手改掉一个测试断言让它变绿、失败后在同一处重试到上下文耗尽。缺的是隔离(γ)、
落地前的闸(已编译在 verify_commit.py)、"做完"的判据与升级规则(γ)。
世界(Σ)
- 实现者看到的全部输入:一张卡(
assets/card_context.md形状)+sdlc_state.py show的摘要 + 该卡的 AC 子集 +allowed_files内的源码。看不到:评审 skill 的提示与判据、隐藏变体集、spec-robustness.md、 其他卡、账本里评审者的发现。这是训练期信息隔离的实现形态(干活的不许看日志)。 - 执行器可换:
self(当前会话,仍遵守隔离——只读卡)、agent(agents/card-implementer.md,全新上下文)、ratchet(需要跑到达标为止的卡)、forge-teams(并行多卡,邻居)。隔离规则对所有执行器相同。 - 红-绿:卡的 AC 子集对应的测试由
/test-suite-generator事先写好并锁;实现前它们必须是红的(基线上跑 一次记录),实现后变绿。测试文件在forbidden_files里——实现者改不了。 - 一卡多 commit 合法(按关注点),但每个 commit 都过
verify_commit.py --card --lock。 - 失败指纹:同一张卡同一失败摘要第二次出现 = 无进展,
sdlc_state.py fail会判 escalate(方案层:重拆或改卡), 不是"再试一次"。 - 关于用户的 Σ:"先把功能做出来再说"= 仍然只在白名单内做;"测试写得不对"= 走变更提案,不是改测试。
判据(φ)
- 卡的
ac_ids对应测试全绿(/qa-reviewer或直接跑测试入口);全套件无回归;lint / 类型 / 构建绿(存在则跑)。 - 每个 commit
verify_commit.py --card <卡> --lock .done_when.lockexit 0。 - diff 内没有卡
forbidden_files的文件;没有新增依赖(有则记notes并进 A 档检查)。 - 残差:实现是否走捷径满足测试(
/spec-gaming-detector在整体验收时看);本 skill 不自评。
原语(Π)
assets/card_context.md—— 交给实现者的输入形状(卡 + 状态摘要 + AC 子集 + 红基线记录)。../../agents/card-implementer.md—— 全新上下文的实现者定义。../commit/scripts/verify_commit.py—— 落地前的闸;../sdlc/scripts/sdlc_state.py card / fail—— 登记与升级。references/executors.md—— 四种执行器的接法与隔离检查表。
门(γ)
- 前置:
cards.lint_passed=true;.done_when.lock存在;该卡 AC 的测试存在且在基线上为红(无测试则notes写明no-tests-for: AC-xxx并在整体验收时补——不许实现者自己写验收测试)。 - done_when(本卡):AC 子集绿 ∧ 全套件无回归 ∧ 每个 commit 过闸 ∧
sdlc_state.py card CARD-xx --status done --commit <sha>。 - 升级:
fail --signal card_test_fail --card CARD-xx --fingerprint <摘要>;返回escalate: true→ 停,写失败报告, 回/plan-cards或交人。绝不绕过。
What ships with it
4 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.
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 · +9 lines e82da52f0cee
- yesterday First seen · 84 lines · 216 tokens per session scan A 55a4cd28968a
implement is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed today), licensed MIT. It adds 216 tokens to every session and 1,925 once invoked, about $0.0011 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
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.
release-safety
Release safety rules. INVOKE WHEN: yarn release, npm publish, release canary, release packages, publishing, skip checks, skip tests. NEVER skip checks or tests without explicit permission.