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 plan-cardsgit 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/plan-cards)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/plan-cards"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/plan-cards.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 | $0.00273 | $0.02144 |
| Opus 5 | $0.00137 | $0.01072 |
| Sonnet 5 | $0.00055 | $0.00429 |
| Haiku 4.5 | $0.00027 | $0.00214 |
Grade A, and why
plan-cards 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan-cards — 自包含的卡，不是设计文档
产物是 cards/CARD-xx.yaml（形状：assets/card_template.yaml）。合格标准只有一条：单独丢给一个没有任何
上下文的 agent，它能干完。本文件写：卡在流水线里是什么、什么算拆对了、原语与出口、进实现前的门。
先拆哪块、拆几张是你的份额。
缺口（Judgment + Capability + Control）
deletion 测试：撤掉本 skill，引擎会写一份平铺的 tasks.md——没有文件归属、没有 AC 子集、两张卡都改
package.json、一张卡要 80k 上下文。并行实现时合并冲突，卡级验收没有对象，白名单执行器无从执行。
缺的是判据（自包含长什么样）、原语（三项 lint）、门（lint 不过不进 implement——sdlc_state.py advance implement 要求 cards.lint_passed）。
世界（Σ）
- 卡 = 子 agent 的 prompt 载荷（SKILL.state：只给卡 + 状态摘要，不给整段历史）。卡里没写的，实现者
不知道；所以
notes要自包含，不引用对话。 - REQ 一卡一主：每个 REQ 只能归一张卡（重复归属 = 两个实现者改同一行为）。AC 子集从
done_when.acceptance按req取。 - 文件级存在性在卡里，不在契约里（C2）：
allowed_files是白名单执行器（verify_commit.py --card）的输入；forbidden_files默认继承done_when.constraints.forbidden_paths+tests/**+ 锁文件。 - 共享文件（lockfile / 配置 / 路由表 / schema）要么归一张卡，要么全部禁改——"卡间无写冲突"必须覆盖它们。
- 卡级验收 ≠ 需求级验收：每张卡只跑 AC 子集；所有卡完成后必须整体跑一次（
/acceptance-fleet）。 depends_on只表示依赖顺序（Σ 第 1 格），不是执行脚本；无依赖的卡可并行。- 投影与其数据源同卡：渲染 / 报告脚本与它读的数据在一张卡里，否则没人能原子地同时改数据的形状与它的
标签。跨卡是例外，例外要
reads_from+depends_on+notes里的接缝风险三样齐全（lint 项 6）。 - 上下文预估：卡 + 相关源码 + AC 子集 + 测试 > 40k → 必拆（lint，不是备注）。
- 这条 40k 会反压契约：一个 REQ 的实现读集若超 40k，"REQ 一卡一主"与"≤ 40k"同时成立就无解。 G2 冻结前就要按分区把这类 REQ 拆开；G2 之后再拆要走变更提案 + 重新签锁。
- 关于用户的 Σ："拆细一点"= 上下文预算更小，不是更多卡；"一张卡做完"= 合法，但仍要过 lint。
判据（φ）
lint_cards.py三项 + 上下文 +ac_ids存在性 +allowed_files非空 + 投影/数据源同卡 → 全过。- 残差（人 / judge）：卡是否真的自包含；
allowed_files是否最小；上下文预估是否诚实。
原语（Π）
scripts/lint_cards.py <cards_dir> [--spec spec.md] [--done-when done_when.yaml] [--dos dos.yaml] [--max-context N] [--repo-root DIR] [--projection-pattern RE]—— exit 0 / 1 / 2。进 implement 前必须跑，过了sdlc_state.py set cards.lint_passed=true。 给--repo-root时会读渲染脚本本身核验reads_from，声明因此可核验而非自述。assets/card_template.yaml—— 卡的具名字段。references/splitting.md—— 拆分启发式（按观察边界 / 按 DOS 对象 / 先契约后 UI / 投影与数据源同卡）、 共享文件处置、上下文估算法、以及 L4 对契约层 REQ 粒度的反压。
仓库地图切片（v0.2.0）
What ships with it
20 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/card_template.yaml 2.1 KB
- eval/fixtures/cards_bad/CARD-01.yaml 289 B
- eval/fixtures/cards_bad/CARD-02.yaml 280 B
- eval/fixtures/cards_good/CARD-01.yaml 312 B
- eval/fixtures/cards_good/CARD-02.yaml 268 B
- eval/fixtures/cards_projection_bad/CARD-01.yaml 436 B
- eval/fixtures/cards_projection_bad/CARD-02.yaml 475 B
- eval/fixtures/cards_projection_bad/CARD-03.yaml 339 B
- eval/fixtures/cards_projection_good/CARD-01.yaml 515 B
- eval/fixtures/cards_projection_good/CARD-02.yaml 721 B
- eval/fixtures/cards_projection_good/CARD-03.yaml 469 B
- eval/fixtures/done_when.yaml 1.4 KB
- eval/fixtures/dos.yaml 163 B
- eval/fixtures/repo/scripts/render_audit.py 330 B runs code
- eval/fixtures/spec.md 150 B
- eval/gate.json 1.5 KB
- eval/report.md 763 B
- references/splitting.md 4.6 KB
- scripts/lint_cards.py 16 KB runs code
- scripts/slice_agent_map.py 4.9 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 · +16 lines · +34 tokens per session e1914dbc8dc5
- yesterday First seen · 82 lines · 239 tokens per session scan A 83d361e54fe7
plan-cards is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed today), licensed MIT. It adds 273 tokens to every session and 2,144 once invoked, about $0.0014 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.