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/andrei-isvoran96/claude-skill-labWrote 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/andrei-isvoran96/claude-skill-lab/pr)<a href="https://agentmods.dev/commands/andrei-isvoran96/claude-skill-lab/pr"><img src="https://agentmods.dev/badge/commands/andrei-isvoran96/claude-skill-lab/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/andrei-isvoran96/claude-skill-lab/pr"><img src="https://agentmods.dev/badge/commands/andrei-isvoran96/claude-skill-lab/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 | $0.00000 | $0.00464 |
| Opus 5.5 | $0.00000 | $0.00186 |
| Sonnet 5.5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00046 |
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 2mo 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
Create a pull request from the current branch towards origin/<BASE_BRANCH>.
Steps
-
Validate the current branch. Run
git branch --show-current. If the current branch ismainor<BASE_BRANCH>, warn the user and stop — PRs should come from feature/bug branches. -
Fetch latest and check remote tracking:
git fetch origin <BASE_BRANCH> -
Check if the branch is pushed to origin. Run
git statusto see if the branch tracks a remote. If not, push it first:git push -u origin $(git branch --show-current) -
Gather context for the PR. Run these in parallel:
git log --oneline origin/<BASE_BRANCH>..HEADto see all commits on this branchgit diff origin/<BASE_BRANCH>...HEAD --statto see changed filesgit diff origin/<BASE_BRANCH>...HEAD(piped throughhead -6000) to see the full diff
-
Draft the PR title and body by analyzing ALL commits and changes (not just the latest commit):
- Title: short, under 70 characters, conventional format (e.g.
fix: prevent edges disappearing when deleting branched node) - Body: use the template below
- If the branch name contains an issue number (e.g.
bug/207-...), includeFixes #207in the body
- Title: short, under 70 characters, conventional format (e.g.
-
Create the PR using
gh pr create:gh pr create --base <BASE_BRANCH> --title "the title" --body "$(cat <<'EOF' ## Summary <1-3 concise bullet points describing what changed and why> ## Test plan <Bulleted checklist of manual or automated verification steps> EOF )" -
Report the PR URL to the user so they can review it.
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.
- 2mo ago First seen · 45 lines · 0 tokens per session scan A 0a5be3afe6a6
pr is a command published in the GitHub repository andrei-isvoran96/claude-skill-lab (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 464 tokens. 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.
pr compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prandrei-isvoran96/claude-skill-lab | Command | 1 | 5mo ago | MIT | A | 0 | Claude Code |
| merge-conflict-analysisrjmurillo/ai-agents | Command | 49 | today | MIT | A | 0 | GitHub Copilot |
| release-notesOpenHands/extensions | Command | 178 | yesterday | MIT | A | 44 | Claude Code |
| repo-audittractorjuice/arc-kit | Command | 2.3k | today | none | A | 29 | Claude Code |
| commitechoVic/blade-code | Command | 181 | 26d ago | MIT | A | 8 | Claude Code |
| propsmill/infrahub-mcp | Command | 10 | yesterday | Apache-2.0 | A | 18 | Claude Code |
| codex-reviewoalders/kitchen-sink | Command | 5 | 5d ago | MIT | A | 41 | Claude Code |