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.
npx skills add JiaWeiXie/swarm-pi-code-plugin --skill swarm-pi-discovergit clone --depth 1 https://github.com/JiaWeiXie/swarm-pi-code-pluginWrote 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/jiaweixie/swarm-pi-code-plugin/swarm-pi-discover)<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>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 | $0.00051 | $0.00446 |
| Opus 5 | $0.00026 | $0.00223 |
| Sonnet 5 | $0.00010 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00045 |
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.
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.
- Write a self-contained discovery brief with unknowns, constraints, evidence acceptance criteria, freshness, user gates, and a sequential experiment plan.
- Run
$RUNNER discover --host "$HOST" --role analyst --prompt-file "$PROMPT_FILE" --execution-mode supervised --approval-mode "$APPROVAL_MODE" --json. - 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.
- 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.
- Complete only when the result is
supported,refuted, orinconclusiveand includes all three stage reports plus a final gate decision. Every experiment artifact remainsdeliverable: 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.
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.
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.
- 7d ago First seen · 35 lines · 51 tokens per session scan A 4c5417548983
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.
Other skills, from other repositories
smoke
Runs a three probe live smoke wave after a plugin update and reports gate chain health before real work rides it.
test-web-ui
Automated web QA skill: analyzes a website or project, generates end-user use cases, derives a structured test plan, executes tests via Playwright browser automation, and produces a full HTML/Markdown QA report with screenshots and pass/fail results. TRIGGER this skill whenever the user asks to: test a website, run QA…
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
ask-tester
Dispatches the tester agent to write and run tests: unit, integration, and end-to-end.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
verify-samples-tool
How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.