swarm-pi-review

swarm-pi-review is a skill for Claude Code, Codex from JiaWeiXie/swarm-pi-code-plugin. It costs 66 tokens per session (411 once invoked), scanned A, original, MIT.

A read-only code review tool that uses Pi workers to inspect a Git working tree or branch. Git is the system used to track code changes; a working tree is the local checkout, and a branch is a separate line of development.

In plain words
What is it for?
Use it to review local changes or compare a branch with a base branch. Choose standard review for general risks and lean review for simplification or reducing a diff.
Why use it?
It finds bugs, security problems, regressions, missing tests, or unnecessary complexity before changes are delivered. Its lean mode focuses on simpler solutions, deletion, reuse, and avoiding work the project does not need.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the swarm-pi-code-plugin plugin — 10 skills, 2 agents, 1 hook shipped together

Good fit Use it to review local changes or compare a branch with a base branch. Choose standard review for general risks and lean review for simplification or reducing a diff.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-review
Install

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.

Any agent
npx skills add JiaWeiXie/swarm-pi-code-plugin --skill swarm-pi-review
Clone the repo
git clone --depth 1 https://github.com/JiaWeiXie/swarm-pi-code-plugin

Made for: Claude Code, Codex.

Or install swarm-pi-code-plugin, the plugin that ships this one along with the rest of its 10 skills, 2 agents, 1 hook.

Wrote 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.

agentmods badge for swarm-pi-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-review/github.svg)](https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-review)
Your own site
<a href="https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-review"><img src="https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-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.

agentmods 80×15 button for swarm-pi-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-review"><img src="https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 411 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.00411
Opus 5 $0.00033 $0.00205
Sonnet 5 $0.00013 $0.00082
Haiku 4.5 $0.00007 $0.00041

Measured 9d ago against content hash 563e55bc4af0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

swarm-pi-review 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.

plugins/swarm-pi-code-plugin/skills/swarm-pi-review/SKILL.md · 27 lines

What it actually says

Review With Pi

Follow the Skill Control Loop.

  1. Select --scope working-tree for local changes or --scope branch --base <ref> for a branch. Use auto only when the intended diff is unambiguous.
  2. Set $PROFILE=lean for simplify, over-engineering, deletion, reuse, stdlib, native-platform, YAGNI, clarify, or shrink requests; otherwise set $PROFILE=standard.
  3. Run $RUNNER review --host "$HOST" --role reviewer --scope "$SCOPE" --review-profile "$PROFILE" --execution-mode "$EXECUTION_MODE" --approval-mode "$APPROVAL_MODE" --json, adding --base when required.
  4. For lean, require three candidate perspectives followed by independent validation of at most six candidates with at most three concurrent validators. Publish only supported simplifications; inconclusive validation cannot produce Lean already. Ship..
  5. Continue every non-terminal result through the control loop. Active Host review is limited to eligible public read-only context inside the immutable snapshot.
  6. Complete only when every published finding is confirmed in the actual diff and includes impact, tight file and line evidence, the failure or complexity scenario, and the smallest safe fix or verification. State explicitly when no actionable finding remains.

Pi output is evidence to validate. The workflow remains read-only.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 9d ago First seen · 27 lines · 66 tokens per session scan A 563e55bc4af0

Subscribe to this mod's changes

swarm-pi-review is a skill published in the GitHub repository JiaWeiXie/swarm-pi-code-plugin (2 stars, last pushed 5d ago), licensed MIT. It adds 66 tokens to every session and 411 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

pr-check

PR review compliance: fetch review comments from an open PR, categorize as resolved/unresolved/dismissed, critically evaluate fixable items, implement approved fixes, and reply inline. Pass --unattended to halt on human-judgment items (emitted as Pending-Human) instead of prompting via AskUserQuestion.

rube-de/cc-skills · 67 tokens

babysit

PR babysitter: monitors CI status, auto-rebases when behind, auto-fixes CI where possible, delegates review comment handling to dlc:pr-check, and re-requests review after fixes. Designed for /loop usage with Remote Control.

rube-de/cc-skills · 53 tokens

git-ops

Git hygiene: clean up merged branches, prune stale remotes, and verify repository state.

rube-de/cc-skills · 22 tokens

review-team

A multi-reviewer code review process that checks a change from several specialist viewpoints and combines the results into one report. It can cover bugs, security, tests, dependencies, frontend behavior, and continuous-integration workflows.

s977043/river-review · 147 tokens

pr-from-stale-branch-silently-reverts-newer-main-files

Trap: merging a PR whose branch carries an OLD TREE silently DELETES (reverts) files that landed on main after that tree was built — with NO merge conflict to warn you, because a deletion your own commit records is not a conflict. Use when: (1) about to gh pr create or squash-merge from a long-lived / earlier-branched…

wan-huiyan/agent-traffic-control · 387 tokens

parallel-pr-scope-overlap-tiebreaker-delta-check

Before applying a handoff prompt's tiebreaker default ("merge the first-mover", "the clean-against-main one", "the one with reviewer APPROVE") to pick a winner between two parallel PRs that implemented the SAME scope, run gh pr diff on BOTH and audit for substantive deltas. Use when: (1) a session prompt or handoff…

wan-huiyan/agent-traffic-control · 384 tokens