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 chan4lk/specclaw --skill prgit clone --depth 1 https://github.com/chan4lk/specclawWrote 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/chan4lk/specclaw/pr)<a href="https://agentmods.dev/skills/chan4lk/specclaw/pr"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/pr.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 | $0.00074 | $0.00988 |
| Opus 5 | $0.00037 | $0.00494 |
| Sonnet 5 | $0.00015 | $0.00198 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
pr 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 6d 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
specclaw pr
First, run specclaw-ensure-init .specclaw — idempotently creates .specclaw/ if it doesn't exist (silent if already initialized; auto-inits using the current directory's basename as the project name).
Create a GitHub PR for a verified change. Requires verify-report.md (build + verify must complete first).
- Code review block (conditional): Read
workflow.code_review_blockfrom.specclaw/config.yaml. Iftrue:- Check if
.specclaw/changes/<change>/review-report.mdexists. If it does not exist, warn: "code_review_block is enabled but no review-report.md found — run /specclaw:verify first" and continue. - If
review-report.mdexists and verdict isCHANGES_REQUESTED, abort with: "PR blocked: code review verdict is CHANGES_REQUESTED. Fix BLOCK findings in review-report.md then re-run /specclaw:verify." List all BLOCK findings from the report before aborting.
- Check if
- Validate:
specclaw-validate-change .specclaw <change> pr. Exits with a warning (exit 0) if a PR already exists for this change. Fails ifverify-report.mdis missing. - Run:
specclaw-pr .specclaw <change>— always create the PR through this script, never hand-rollgh pr create.specclaw-prstages and commits the full.specclaw/changes/<change>/planning trail (proposal, spec, design, tasks, status, verify-report) into the branch and aborts if any of it is left uncommitted — a rawgh pr createskips this and ships a PR missing the proposal artifacts.- First run: prompts for test policy (
none|unit|e2e|both), saves it toconfig.yamlunderpr.test_policy. Never prompts again. - Test enforcement: if policy is not
none, verifiesbuild.test_commandis set and thatverify-report.mdcontains test evidence. Fails (strict) or warns (non-strict) if evidence is missing. - Version bump: if
plugin.version_filesis set inconfig.yaml, compares each file's"version"against the base branch. If unchanged, auto-bumps the patch version and commits before PR creation. Configure in.specclaw/config.yaml:plugin: version_files: - "plugins/specclaw/.claude-plugin/plugin.json" - ".claude-plugin/marketplace.json" - PR creation: builds title from
proposal.md, body fromspec.md+verify-report.md, runsgh pr create --base main. - GitHub sync: if
github.sync: true, includesCloses #Nin the PR body. - Saves URL: appends
**PR:** <url>tostatus.md.
- First run: prompts for test policy (
- Update project context: After the PR URL is saved, rewrite
.specclaw/context.mdto incorporate decisions from this change:- Run
specclaw-update-context .specclaw <change>— this outputs an LLM prompt. - Feed the prompt to a coding agent that rewrites
context.mdin place (architecture-doc style: replaces stale info, merges new decisions). - If
context.mdchanged, commit it:git add .specclaw/context.md && git commit -m "docs(context): update project context after <change>"and push. - Errors here are non-blocking — warn and continue.
- Run
- Report the PR URL to the user.
CI outer loop (if loop.ci_gate: true): once the PR branch is pushed, the CI tier of /specclaw:loop (Step 3 / specclaw-loop ci-poll) polls GitHub Actions checks and iterates fixes until they are green, or loop.ci_max_iterations / loop.ci_timeout_seconds halts and escalates. This is a cross-reference only — PR creation above is unchanged, and nothing extra runs when loop.ci_gate is false.
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.
- 6d ago First seen · 36 lines · 74 tokens per session scan A fd1e87de8280
pr is a skill published in the GitHub repository chan4lk/specclaw (12 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 988 once invoked, about $0.0004 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
pair-review
Standalone cross-review of current git changes with a fresh read-only reviewer, optionally adding Codex's native review. ONLY runs when the user explicitly types /pair-review. NEVER activate automatically.
babysit
Watch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.
agent-pr-manager
Agent skill for pr-manager - invoke with $agent-pr-manager.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.