What is swarm-pi-implement?

A tool for making an explicitly approved change in an existing Git repository. It uses Pi to carry out scoped edits while preserving the user's existing changes.

Use it for an authorized fix, feature change, or refactor in an existing repository. It supports planning verification with unit, integration, contract, regression, end-to-end, or property tests, as well as using existing checks without adding new tests.

It keeps implementation tied to clear acceptance checks and the project's testing preference. It also separates changing files from later delivery actions such as committing or pushing.

swarm-pi-implement — Skill for Claude Code and Codex by JiaWeiXie: A tool for making an explicitly approved change in…

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.

agentmods

npx agentmods add skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-implement

Any agent

npx skills add JiaWeiXie/swarm-pi-code-plugin --skill swarm-pi-implement

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-implement.svg)](https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-implement)

Your own site

<a href="https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-implement"><img src="https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-implement.svg" alt="Measured on agentmods" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 553 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00059	$0.00553
Opus 5	$0.00030	$0.00277
Sonnet 5	$0.00012	$0.00111
Haiku 4.5	$0.00006	$0.00055

Measured 4d ago against content hash 3d760df75487, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

swarm-pi-implement 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 4d 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-implement/SKILL.md · 38 lines

What it actually says

Implement With Pi

Follow the Skill Control Loop. Load Resource-Aware Execution before expensive or recursive verification.

Confirm explicit mutation intent and an existing Git repository. Preserve user changes in place; route a new non-Git project to scaffold.
Add only missing scope, observable acceptance criteria, protected boundaries, and the smallest verification plan to the temporary prompt.
Run $RUNNER implement --host "$HOST" --role executor --prompt-file "$PROMPT_FILE" --execution-mode supervised --approval-mode "$APPROVAL_MODE" --json; with explicit user choice, append --implementation-profile prewalk to preserve exploration, TODOs, and the first edit through an in-session handoff.
Before implementation, honor the configured testing preference. If no invocation-level choice exists, ask the Host to offer 2–3 fitting methods (unit, integration, contract, regression, E2E, or property) plus no-new-tests. TDD is optional; no-new-tests still requires relevant existing checks.
Continue every non-terminal result through the control loop. Background is reserved for an explicitly requested, project-enabled mechanical-executor, with the assigned worktree left exclusively to Pi.
Inspect the actual diff, changed files, runtimeSideEffects, verification, and artifact. Exit code 5 presents isolated-head and isolated-snapshot without choosing. workspace-unborn-head routes to scaffold or approved adoption before resume.
A safe-dirty job-owned worktree is deliverable only after the verified, reversible artifact diff is shown and the user approves $RUNNER jobs materialize --job <id> --json.
Complete only when the actual diff satisfies the request, targeted Host-owned verification passes, and delivery state is explicit. deliverable: false artifacts remain isolated; commit, merge, and push remain Host-owned.

Host Assistance stays correlated and consume-once. Its evidence, assessment, or recommendation cannot expand policy or intent.

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.

agents/openai.yaml 228 B

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.

4d ago First seen · 38 lines · 59 tokens per session scan A 3d760df75487

Subscribe to this mod's changes

swarm-pi-implement is a skill published in the GitHub repository JiaWeiXie/swarm-pi-code-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 59 tokens to every session and 553 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.

Multi-Agent Orchestration claude claude-code-plugin codex codex-plugin

review-team

6つの専門レビュアーロールを並列実行し、consensusLevel（複数ロールの合意度）と Tech Lead レポート（top3指摘・blindSpots・consensusSummary）で結果を統合するマルチエージェントレビュー entry skill。 Parallel multi-role review with consensus scoring (consensusLevel) and Tech Lead report. Use when a major release needs exhaustive multi-angle review, or when a single-perspective review…

s977043/river-review · 147 tokens

gaia-release

Use when testing, validating, or publishing Gaia releases -- "install local", "pre-release", "dry-run", "release", RC, stable, plugin dry-run.

metraton/gaia · 37 tokens

diagram-builder

Use when the user wants to build or extend a diagram deck of nested sections and components authored in plain YAML — an architecture map, a timeline diagram, a planner board, a process-flow diagram, a slide-style presentation, a side-by-side comparison, or a mind-map. Not for charts, plots, or numeric/data…

metraton/gaia · 121 tokens

swarm-pi-implement