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 specsnl/agent-specs --skill create-prgit clone --depth 1 https://github.com/specsnl/agent-specsWrote 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/specsnl/agent-specs/create-pr)<a href="https://agentmods.dev/skills/specsnl/agent-specs/create-pr"><img src="https://agentmods.dev/badge/skills/specsnl/agent-specs/create-pr/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/specsnl/agent-specs/create-pr"><img src="https://agentmods.dev/badge/skills/specsnl/agent-specs/create-pr.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 | $0.00067 | $0.00783 |
| Opus 5.5 | $0.00027 | $0.00313 |
| Sonnet 5.5 | $0.00013 | $0.00157 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
create-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 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Pull Request
Audit the repository's PR configuration, verify CI is green, then open the PR.
Phase 1 — Audit PR requirements
Read the repository's PR configuration before touching git.
1a. Read all workflow files
find .github/workflows -name "*.yml" -o -name "*.yaml" | sort
For each workflow file, identify:
- Jobs triggered by
pull_requestevents - Any title validation steps (e.g.
pr-title-checker,action-semantic-pull-request) - Required status checks that must pass
1b. Check PR title format
Look for .github/pr-title-checker-config.json and read it to extract the allowed prefix pattern.
If not found, check for a workflow step that enforces title format and read its config.
1c. Check branch rules
Read .github/rulesets/*.json if present. Note:
- Required merge method (Specs projects use merge commits only — no squash/rebase)
- Required status checks
1d. Summarise before proceeding
Report:
- What CI jobs will run on this PR
- Required title format / prefix
- Any merge restrictions
Phase 2 — Run CI checks locally
Invoke the ci-green-check skill — it runs whatever checks are discovered in Phase 1 that can run
locally, and hands off to php-checks in Laravel/PHP projects.
Do not proceed to Phase 3 if any check fails.
Phase 3 — Ensure branch and commits are ready
-
Confirm the working tree is clean (
git status) -
Confirm not on
main/master/develop— if so, create a branch first:git checkout -b kebab-case-descriptionUse the Linear issue slug as the branch name if one was provided.
-
Commit messages lead with a single subject line. A body is allowed when it adds context the subject can't carry, but keep it succinct — a few lines at most.
-
Never add a
Co-Authored-Bytrailer or mention Claude in any commit message.
Phase 4 — Create the PR
git push -u origin HEAD
gh pr create --title "PREFIX: short description" --body "$(cat <<'EOF'
## Summary
- ...
EOF
)"
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 Changed · +6 lines 05f90ffc90e1
- 1mo ago First seen · 102 lines · 67 tokens per session scan A 7bf804b5dbbc
create-pr is a skill published in the GitHub repository specsnl/agent-specs (2 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 783 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…