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 flanliulf/SpecLite --skill speclite-canonical-source-governance-runnergit clone --depth 1 https://github.com/flanliulf/SpecLiteWrote 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/flanliulf/speclite/speclite-canonical-source-governance-runner)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-canonical-source-governance-runner"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-canonical-source-governance-runner/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/flanliulf/speclite/speclite-canonical-source-governance-runner"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-canonical-source-governance-runner.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 | $0.00101 | $0.00908 |
| Opus 5.5 | $0.00040 | $0.00363 |
| Sonnet 5.5 | $0.00020 | $0.00182 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
speclite-canonical-source-governance-runner 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 1mo 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.
What it actually says
[Overview(技能说明)]
在 canonical-source-change-check hook 发现 assets/source/speclite/ 变化后,执行完整 canonical source governance workflow。它不是只读 checker,而是把治理映射、影响面矩阵、人工决策记录、定点修订和验证命令串成一个落地流程。
[Core Capabilities(核心能力)]
- 治理分类:读取 assets/source/speclite/canonical-governance.json 和 docs/reference/canonical-source-governance.md,区分 D0、D1、D2。
- 影响面矩阵:根据 git diff 判断变更触及 canonical source、module discovery、hook source、public docs、living legacy、frozen history 或 release evidence。
- Hook 后续执行:消费 canonical-source-change-check 的 warning,明确下一步是治理 runner,而不是只跑只读 checker。
- 定点修订:在用户授权执行时,只修改影响面矩阵要求的文件,不扩大到无关源码。
- 决策记录:对 D1 / D2 面向记录 updated、skipped 或 historical snapshot,避免把历史记录误当当前事实。
- 验证收口:运行 canonical checker 的 warn / strict 模式、相关 lint、focused tests、build、full tests、packaging check 和 git diff --check。
[Workflow(执行流程)]
本 Skill 使用顺序工作流与治理检查组合。详细步骤、矩阵和停止条件见 references/canonical-source-governance-runner-workflow.md。
1. 读取治理映射和治理文档。
2. 读取 git diff / staged diff / untracked files,限定到本轮 canonical source 变更和相关派生文件。
3. 生成影响面矩阵,先处理 `D0`,再处理 `D1` / `D2`。
4. 若需要修改,按矩阵定点更新 canonical source、docs、fixtures、tests、checker 或 packaging manifest。
5. 使用 `templates/decision-record.md` 结构记录 `D1` / `D2` 的更新或跳过理由。
6. 运行 warn 与 strict checker,并执行相关验证命令后总结。
[Notes(注意事项)]
- 本 Skill 只用于维护 SpecLite 自身 canonical source,不属于目标项目默认 SDLC runtime install set。
- 本地 hook 仍是 warning-only;阻断语义来自 strict checker、CI 或 release gate。
- D0 问题必须用文件证据和脚本结果收口,不凭记忆更新数量。
- D1 / D2 问题必须留下决策理由;不能把旧 PLAN.md、EXPERIMENTS.md、handoff snapshot 静默改成当前事实。
- 修改 support skill 时,不要把它加入 core / sdlc module-help.csv,除非产品决策明确要求安装到目标项目。
[Generation Metadata(生成信息)]
本 Skill 由 speclite-skill-creator 自动生成。如需修改,必须同步更新 SKILL.md 与 SKILL.en.md,并同步 assets/source/speclite/support-skills/speclite-canonical-source-governance-runner/ 与实际安装副本。
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.
- 1mo ago First seen · 41 lines · 101 tokens per session scan A c1053615c827
speclite-canonical-source-governance-runner is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 14d ago), licensed MIT. It adds 101 tokens to every session and 908 once invoked, about $0.0004 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 2026-09-16.
Other skills, from other repositories
development-scheduler
A workflow for coordinating multi-role coding work through Herdr, a task scheduler, and repo-harness sessions. It assigns implementation, review, and handoff tasks while checking permissions and evidence.
PR Standards
Pull request description, review depth, and merge standards so every PR carries enough context to review and merge safely.
Commit Format
A simple Conventional Commits style for clear, scannable commit history.
Git Workflow
Lightweight branch naming and pull-request-vs-direct-push guidance for fast solo/small-team iteration.
project-flow-ops
CIEL's coordination layer for triaging issues, PRs, and tasks across GitHub and internal tracking systems (e.g., Linear).
proposal-filing
File a new Lorekeeper proposal ticket — create markdown, create GitHub issue, commit, push. Use when requesting a new feature, filing a bug, or submitting a product idea.