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-check-canonical-source-changegit 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-check-canonical-source-change)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-check-canonical-source-change"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-check-canonical-source-change/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-check-canonical-source-change"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-check-canonical-source-change.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 | $0.00091 | $0.00977 |
| Opus 5 | $0.00046 | $0.00489 |
| Sonnet 5 | $0.00018 | $0.00195 |
| Haiku 4.5 | $0.00009 | $0.00098 |
Grade A, and why
speclite-check-canonical-source-change 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 12d 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）]
只读检查 assets/source/speclite/ 作为 SpecLite canonical source 发生新增或修改后的闭环一致性。它把 canonical skill、hook、agent、fixture、docs 和 release packaging 的派生关系集中成一份可执行检查清单，避免 root counts、module-help.csv、hook descriptor、安装 fixture 或发布 manifest 漂移。
[Core Capabilities（核心能力）]
- Root counts 对齐：统计 core-skills、sdlc-skills、support-skills 和 hooks，确认默认安装 baseline 仍是 core+sdlc。
- module-help.csv 对齐：检查 core / sdlc package roots 是否都有 help row，并报告重复、缺失或未知 row。
- Hook source 完整性：检查每个 canonical hook package 的 README.md、hook-manifest.json、runner.mjs、Claude/Codex fragment 和 manifest id。
- Agent lint 路由提醒：识别 speclite-agent-* 变更时提醒使用 speclite-agent-lint，避免套用 workflow-only 规则。
- 派生产物扫描：检查 CORE_SDLC_BASELINE_ENTRY_COUNT、文档旧数字、fixture 旧数字、legacy Codex hook array shape 和 release/packaging-manifest.json。
- 验证命令建议：输出 scoped script、skill density、focused tests、build、full tests、packaging check 和 git diff --check。
[Workflow（执行流程）]
1. 确认仓库根目录，默认在 SpecLite 仓库根运行。
2. 读取 references/canonical-change-checklist.md，确认本次 canonical 变更涉及 skill、hook、agent、docs、fixtures 或 packaging 哪些面。
3. 运行只读脚本：
node assets/source/speclite/support-skills/speclite-check-canonical-source-change/scripts/check_canonical_source_change.mjs --project-root . --scope all --format json
4. 对脚本 findings 做人工复核：warning 表示需要同步派生产物；failure 表示脚本本身无法读取必要输入。
5. 若涉及 Agent 定义包，补跑：
python3 assets/source/speclite/support-skills/speclite-agent-lint/scripts/check_agent_skill.py <agent-dir>
6. 若涉及普通 Skill 包，补跑：
python3 assets/source/speclite/support-skills/speclite-skill-lint/scripts/check_skill_density.py <skill-dir>
7. 完成修复后重新运行 Step 3，并按脚本输出的 recommended commands 执行聚焦测试和 release packaging check。
[Notes（注意事项）]
- 本 Skill 只读，不直接修改 canonical source 或派生产物。
- support-skills 不进入默认目标项目 skill mirrors；默认安装 baseline 只计算 core+sdlc。
- Hook guardrail 是 deterministic 保护层，不替代开发流程或人工 review。
- canonical-source-change-check hook 是 warning-only：提醒运行本 Skill 和验证命令，不阻断 Claude/Codex 会话。
- 检查报告必须用实际文件和脚本结果支撑，不凭记忆更新 sdlc、core、support 或 total 数字。
[Generation Metadata（生成信息）]
本 Skill 由 speclite-skill-creator 体系维护并纳入 SpecLite support-skills。修改时必须同步 SKILL.md、SKILL.en.md、CHANGELOG.md、references/ 和 scripts/。
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.
- 12d ago First seen · 43 lines · 91 tokens per session scan A b72c2fad9cdf
speclite-check-canonical-source-change is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 977 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
lain
Structural code intelligence for AI coding agents. Use this skill when the user wants to understand how a codebase is organized (modules, call graphs, file dependencies), find where to start reading, trace the impact of a change, find code by meaning, or understand what a symbol does in its full context. Do NOT use…
botpipe-workflow-authoring
Author, review, and improve Botpipe workflows. Use when Codex is asked to create packaged or workspace-local Botpipe workflows, convert codebases into workflows, design provider-heavy producer/verifier steps, write Botpipe prompts/contracts, inspect Botpipe traces, or apply Codex CLI/gpt-5.5 workflow patterns.
pre-merge
The CI gate. Takes a feature branch from "eng says done" to "PR open against staging with green checks". Runs the project's preflight-resolved pipeline from devkit/policy.json components[]: sync → parallel correctness + security waves → coverage → regression tail → security/migration → PRD-consistency → open PR. Emits…
intake
The planning front-door. Captures feature ideas and bugs as graded rows in the root INTAKE.md ledger. Use it when the user says "log an idea", "capture a bug", "add to the backlog", "note this down", "track this feature", or invokes /intake. Owns the requirements interview — fleshes out thin ideas, proactively…
merge
The ship gate — the only skill that merges. --staging merges the feature→staging PR on green CI, deploys, verifies, emits a human test script and stamps the staging sign-off on approval. --production ships the double-confirmed release to main and deploys production. Never self-certifies staging; nothing reaches main…
msg
Root menu for msg skills, plus harness modes. --init is the one-time project bootstrap — use it when the user says "initialise project", "bootstrap repo", "set up the framework", "start a new project", or asks to set up project structure in an empty repo. Other modes: --init-staging (add a staging branch), --update…