Borrowing it
Nothing to install: this file belongs to tugrulguner/summonpot. 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/tugrulguner/summonpot/main/.claude/skills/pr-review/SKILL.mdgit clone --depth 1 https://github.com/tugrulguner/summonpotWrote 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/tugrulguner/summonpot/pr-review)<a href="https://agentmods.dev/skills/tugrulguner/summonpot/pr-review"><img src="https://agentmods.dev/badge/skills/tugrulguner/summonpot/pr-review/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/tugrulguner/summonpot/pr-review"><img src="https://agentmods.dev/badge/skills/tugrulguner/summonpot/pr-review.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 | $0.00057 | $0.00748 |
| Opus 5 | $0.00028 | $0.00374 |
| Sonnet 5 | $0.00011 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
pr-review scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
base = subprocess.run(["git","show",f"origin/main:{f}"],capture_output=True,text=True).stdout How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
summonpot pull request mechanics
Opening one
Every user-facing change needs a Towncrier fragment. When the change has a tracking issue, use its number:
changelog.d/<issue-number>.<type>.md
For a small direct change without an issue, generate a unique orphan fragment before opening the pull request:
uv run towncrier create +.changed.md
Replace changed with added, deprecated, removed, or fixed when appropriate. Numeric
fragments must name an issue, not a pull request. Non-user-facing changes carry the
skip-changelog label instead. Dependabot is exempt by label already.
Do not add Claude co-author trailers or "Generated with" lines to commits or PR bodies.
Stacked branches
Chains are normal here. Base each PR on its parent, not on main.
CI only runs on PRs targeting main. A stacked PR shows one green check — the
changelog one — and its real CI fires when it is retargeted after its parent merges.
Run make check locally and say so in the PR.
After a parent is squash-merged
The child still carries the parent's original commits, which no longer match the
squashed commit on main, so GitHub reports conflicts. Do not resolve them — replay
only the child's own commits:
git log --oneline origin/main..origin/<child> # find the old parent tip
git rebase --onto origin/main <old-parent-tip> <child>
Prefer merge commits for chains, which keeps SHAs and avoids this entirely.
Resolving conflicts
Keeping both sides mechanically works for import blocks and pure appends. Everywhere else it splices function bodies together and produces code that still parses. It has silently deleted five tests in this repo.
After any conflict resolution:
python3 - <<'PY'
import re, subprocess, pathlib, glob
def names(s): return set(re.findall(r"^def (test_\w+)", s, re.M))
for f in glob.glob("tests/test_*.py"):
base = subprocess.run(["git","show",f"origin/main:{f}"],capture_output=True,text=True).stdout
if base:
lost = names(base) - names(pathlib.Path(f).read_text())
if lost: print(f, sorted(lost))
PY
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 · 89 lines · 57 tokens per session scan A 9b3f55cd03bb
pr-review is a skill published in the GitHub repository tugrulguner/summonpot (3 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 748 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
setup-pre-commit
Use when bootstrapping or extending the pre-commit hook chain (Husky + lint-staged + Prettier + typecheck + integration tests) for an EVOKORE-style TypeScript repo, including detecting an existing setup, surfacing the diff, and never silently overwriting a configured chain.
cli-command
Design, implement, or review Composio CLI commands under ts/packages/cli using Effect, @effect/cli, services, output conventions, configuration and environment variables, and local vendor references. Use for CLI command UX, command wiring, service changes, or CLI source edits. Do not use for CLI E2E-only work; use…
ring:creating-worktrees
Creating an isolated git worktree for parallel branch work: selects the directory by priority order, verifies/adds .gitignore safety, auto-installs the detected toolchain's dependencies, runs a baseline test, and reports readiness. Use before a feature that needs isolation from the main workspace or before executing…
respond-to-pr-comments
Respond to pull request review comments on GitHub or Azure DevOps Services. Reads review threads, validates each, proposes fixes or explanations, applies changes with user confirmation, and updates thread status via the platform's API. Use when the user wants to address PR feedback or resolve review threads.
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
open-code-review
Use Alibaba Open Code Review (ocr) to review git diffs, staged changes, branches, or scan a workspace, then summarize findings and optionally fix high-confidence issues.