swarm-pi-plan

swarm-pi-plan is a skill for Claude Code, Codex from JiaWeiXie/swarm-pi-code-plugin. It costs 49 tokens per session (295 once invoked), scanned A, original, MIT.

A read-only planning tool for turning a well-understood software change into a concrete implementation brief. It covers scope, alternatives, constraints, checks for success, risks, and decisions still needed.

In plain words
What is it for?
Use it to plan an implementation, migration, or architecture change in an existing repository. Each proposed step identifies affected code, dependencies, verification, risks, rollback, and open decisions.
Why use it?
It reduces the chance of starting implementation with missing requirements or unclear assumptions. It also keeps supporting evidence, unknowns, and citations attached to the plan.

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 plan an implementation, migration, or architecture change in an existing repository. Each proposed step identifies affected code, dependencies, verification, risks, rollback, and open decisions.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-plan.svg)](https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-plan)
Your own site
<a href="https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-plan"><img src="https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 295 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 $0.00049 $0.00295
Opus 5 $0.00024 $0.00148
Sonnet 5 $0.00010 $0.00059
Haiku 4.5 $0.00005 $0.00030

Measured 7d ago against content hash 0102cc8c2258, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

swarm-pi-plan 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 7d 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-plan/SKILL.md · 24 lines

What it actually says

Plan With Pi

Follow the Skill Control Loop.

  1. Inspect enough repository context to write a concrete brief with scope, alternatives, constraints, observable acceptance criteria, and known user decisions. Evidence-poor requirements route to discover.
  2. Run $RUNNER plan --host "$HOST" --role planner --prompt-file "$PROMPT_FILE" --execution-mode "$EXECUTION_MODE" --approval-mode "$APPROVAL_MODE" --json, adding --discovery-from <job-id> only for a verified final-gated DiscoveryResult.
  3. Continue every non-terminal result through the control loop. Active Host review is limited to eligible public read-only context inside the immutable snapshot.
  4. Complete only when each proposed step names its repository surface, observable verification, dependencies, risk or rollback, and any assumption still requiring a user decision.

Preserve citations and unknowns from Host evidence. Implementation is a new routed request.

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. 7d ago First seen · 24 lines · 49 tokens per session scan A 0102cc8c2258

Subscribe to this mod's changes

swarm-pi-plan is a skill published in the GitHub repository JiaWeiXie/swarm-pi-code-plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 295 once invoked, about $0.0002 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.