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.
git clone --depth 1 https://github.com/shaharsha/claude-skillsWrote 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/commands/shaharsha/claude-skills/pr)<a href="https://agentmods.dev/commands/shaharsha/claude-skills/pr"><img src="https://agentmods.dev/badge/commands/shaharsha/claude-skills/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/commands/shaharsha/claude-skills/pr"><img src="https://agentmods.dev/badge/commands/shaharsha/claude-skills/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 | $0.00018 | $0.00486 |
| Opus 5 | $0.00009 | $0.00243 |
| Sonnet 5 | $0.00004 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00049 |
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 9d 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
Commit the changes, push the branch, and open a PR. Then monitor CI until the checks complete. If a check fails, read the logs, diagnose the root cause, fix it, and re-push. If you cannot fix it after two attempts, stop and explain what is failing.
Then stop. Report the PR number, the pushed head, and the CI result.
⚠️ DO NOT MERGE. This command used to say "once all checks pass, merge the PR" and that was wrong.
Green CI is not an approval. It says the tests that exist passed on that head; it says nothing about whether anyone reviewed the change, whether the plan covered it, or whether the base has moved since. Merging on green alone bypasses every gate this machine's sprint work runs on.
If this is Torque Sprint work, the flow is /worker, and merging is step 8–9 of it:
6 Codex round on the IMPLEMENTATION a round happened iff its .md exists
7 OPEN THE PR <- this command gets you here, and no further
8 the ADJUDICATOR reviews and approves on the exact head, after you re-merge develop
9 YOU merge, then watch the deploy and QA it live
⚠️ An approval is a pair — a diff AND a base — and it expires when either moves. So the order is re-merge → push → report → approved on THAT head → merge immediately. Approving first and re-merging second voids the approval in the act of preparing to use it.
Never --no-verify, never --admin, never push to develop or main directly. Never merge on
silence — an absent answer is not an approval.
For non-sprint work in a personal repo, merging yourself is fine and this command simply stops early; say so and merge deliberately, rather than having a slash command do it as a side effect.
Rewritten 2026-08-12. The previous version instructed an unapproved merge on green CI, in the same command namespace the sprint lanes use.
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.
- 9d ago First seen · 38 lines · 18 tokens per session scan A baeb7227ffb3
pr is a command published in the GitHub repository shaharsha/claude-skills (5 stars, last pushed 11d ago), licensed MIT. It adds 18 tokens to every session and 486 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
handoff
Export a Waybill Bundle by default, or import one when requested.