swarm-pi-discover

swarm-pi-discover is a skill for Claude Code, Codex from JiaWeiXie/swarm-pi-code-plugin. It costs 51 tokens per session (446 once invoked), scanned A, original, MIT.

A research and experiment workflow for resolving unknown requirements or technical claims. It produces evidence through research, controlled experiments, and a final result marked supported, refuted, or inconclusive.

In plain words
What is it for?
Use it when a technical question needs reproducible evidence before design or implementation. It helps investigate requirements, test assumptions, and pass evidence-ready findings to planning.
Why use it?
It prevents decisions from resting on guesses or claims that cannot be reproduced. The workflow records hypotheses, controls, dependencies, commands, measurements, tests, cleanup, and whether the result can be replayed cleanly.

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 when a technical question needs reproducible evidence before design or implementation. It helps investigate requirements, test assumptions, and pass evidence-ready findings to planning.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-discover.svg)](https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-discover)
Your own site
<a href="https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-discover"><img src="https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-discover.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 446 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 $0.00051 $0.00446
Opus 5 $0.00026 $0.00223
Sonnet 5 $0.00010 $0.00089
Haiku 4.5 $0.00005 $0.00045

Measured 7d ago against content hash 4c5417548983, 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-discover 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-discover/SKILL.md · 35 lines

What it actually says

Discover With Pi

Follow the Skill Control Loop and read the Discovery Addendum. Load Resource-Aware Execution before the experiment's expensive or recursive commands.

  1. Write a self-contained discovery brief with unknowns, constraints, evidence acceptance criteria, freshness, user gates, and a sequential experiment plan.
  2. Run $RUNNER discover --host "$HOST" --role analyst --prompt-file "$PROMPT_FILE" --execution-mode supervised --approval-mode "$APPROVAL_MODE" --json.
  3. Continue every approval, gate, Host Assistance request, or timeout through the control loop. Host-first review stays inside the snapshotted scope and exact receipt ceiling.
  4. Require all three schema gates: research Evidence Plan; experiment micro-SDLC; definition and convergence. The experiment contract includes hypothesis, control, locked dependencies, fixture, seed or data hash, exact sequential commands, metrics, tolerance, evidence, tests, cleanup, and reported clean replay.
  5. Complete only when the result is supported, refuted, or inconclusive and includes all three stage reports plus a final gate decision. Every experiment artifact remains deliverable: false; an approved result may enter plan through --discovery-from <job-id>.

Every stage inherits the immutable Job policy. Research, convergence, and Advisor use fresh read-only stage Sandboxes; the isolated experimenter child owns and disposes its Sandbox through the shared Adaptive network authorizer. The parent holds no writer lease.

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 · 35 lines · 51 tokens per session scan A 4c5417548983

Subscribe to this mod's changes

swarm-pi-discover is a skill published in the GitHub repository JiaWeiXie/swarm-pi-code-plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 446 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.