Borrowing it
Nothing to install: this file belongs to ai-sdlc-framework/ai-sdlc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ai-sdlc-framework/ai-sdlc/main/.claude/skills/ai-sdlc-governance/SKILL.mdgit clone --depth 1 https://github.com/ai-sdlc-framework/ai-sdlcWrote 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/ai-sdlc-framework/ai-sdlc/ai-sdlc-governance)<a href="https://agentmods.dev/skills/ai-sdlc-framework/ai-sdlc/ai-sdlc-governance"><img src="https://agentmods.dev/badge/skills/ai-sdlc-framework/ai-sdlc/ai-sdlc-governance/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/ai-sdlc-framework/ai-sdlc/ai-sdlc-governance"><img src="https://agentmods.dev/badge/skills/ai-sdlc-framework/ai-sdlc/ai-sdlc-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 14 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 16 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00031 | $0.01057 |
| Opus 5 | $0.00015 | $0.00528 |
| Sonnet 5 | $0.00006 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
ai-sdlc-governance 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-SDLC Governance Rules
Critical Rules — NEVER violate these
- NEVER merge any pull request. Do not run
gh pr merge,git mergeinto main, or any merge operation. Only create or update PRs. The human merges. - Dismiss PR reviews only with documented reason. You may dismiss reviews when they failed due to infrastructure issues (e.g., API credit exhaustion) or when findings are documented false positives. Always include a clear explanation in the dismissal message. Prefer updating
.ai-sdlc/review-policy.mdfor recurring false positives. - NEVER close issues or PRs. Do not run
gh pr closeorgh issue close. The human decides what to close. - NEVER force push. Do not run
git push --forceorgit push -f. - NEVER delete branches. Do not run
git branch -Dorgit branch -d. - NEVER run destructive git operations. No
git reset --hard,git checkout -- .,git restore ..
These rules are also enforced technically via .claude/hooks/enforce-blocked-actions.sh and .ai-sdlc/agent-role.yaml blockedActions.
Pre-Commit Checklist
Before EVERY commit, run these checks and fix any failures:
pnpm build # TypeScript compilation — catches type errors
pnpm test # All tests must pass
pnpm lint # ESLint — no errors allowed
pnpm format:check # Prettier — run `pnpm format` to fix
Test File Check
Before committing new .ts modules, verify:
- Every new
src/**/*.tsfile (nottypes.ts,index.ts) has tests somewhere - Tests can be in a co-located
.test.tsfile OR in another test file that imports it - Run the relevant tests and confirm they pass before staging
Do NOT rely on CI to catch missing tests — check locally first.
Do NOT commit if any of these fail. Fix the errors first, then commit.
Git Flow
- Always rebase feature branches onto main. Never merge main into a feature branch.
- When updating a feature branch with latest main:
git fetch origin && git rebase origin/main - After rebase with conflicts resolved:
git push --force-with-lease origin <branch> - Never use
gh api pulls/N/update-branchwith merge method. - Keep commit history linear — no merge commits on feature branches.
- Use conventional commits:
feat:,fix:,test:,docs:,chore:,style:
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.
- 10d ago First seen · 96 lines · 31 tokens per session scan A a9e9067d2787
ai-sdlc-governance is a skill published in the GitHub repository ai-sdlc-framework/ai-sdlc (249 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 1,057 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
golang-testing
Go testing best practices including table-driven tests, test helpers, benchmarking, race detection, coverage analysis, and integration testing patterns. Use when writing or improving Go tests.
golang-patterns
Go-specific design patterns and best practices including functional options, small interfaces, dependency injection, concurrency patterns, error handling, and package organization. Use when working with Go code to apply idiomatic Go patterns.
printing-press-score
Score a generated CLI against the Steinberger bar, compare two CLIs side-by-side.
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
use-modern-go
Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.
cymbal
Tree-sitter indexed code navigator. Use the cymbal CLI — not Read, Grep, Glob, or Bash — for finding where symbols are defined, tracing callers and callees, locating interface implementations, understanding the impact of a change, and mapping imports across an existing codebase. Returns precise, token-efficient…