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 agentmods add rules/ai-supervisor-foundry/foundry/pm2git clone --depth 1 https://github.com/ai-supervisor-foundry/foundryWhat 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 | $0.00004 | $0.00216 |
| Opus 5 | $0.00002 | $0.00108 |
| Sonnet 5 | $0.00001 | $0.00043 |
| Haiku 4.5 | $0.00000 | $0.00022 |
Grade A, and why
pm2 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 today.
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
-
PM2 logs check is always non-streamed, non-interactive.
-
Supervisor PM2 Management:
- Supervisor runs via
npm run cli -- start(uses tsx to run TypeScript directly, NOT a compiled binary) - Start:
pm2 start ecosystem.config.js(NOTpm2 start dist/index.js) - Stop: First
npm run cli -- halt, thenpm2 stop supervisor, thenpm2 delete supervisor - Restart:
pm2 restart supervisor(after halt if needed) - The supervisor script is defined in ecosystem.config.js and uses npm/tsx, not a compiled dist file
- Supervisor runs via
-
On ANY error when starting/stopping supervisor, immediately halt and stop:
npm run cli -- halt --redis-host localhost --redis-port 6499 --state-key supervisor:state --queue-name tasks --queue-db 2pm2 stop supervisorpm2 delete supervisor
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.
- today First seen · 17 lines · 4 tokens per session scan A 004f6b720876
pm2 is a cursor rule published in the GitHub repository ai-supervisor-foundry/foundry (11 stars, last pushed 1mo ago), licensed MIT. It adds 4 tokens to every session and 216 once invoked, about $0.0000 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 2026-09-02.
Other cursor rules, from other repositories
workflow
Compatibility shell — routes tasks to skill-based-architecture's self-hosted SKILL.md at repo root.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
cursorrules
Cursor rule "cursorrules" from evolution-foundation/evo-ai, covering evo ai - project rules and structure, main technologies, project structure, code standards and language requirements.
react_hooks
React Hooks best practices for frontend package.
use-bun-instead-of-node-vite-npm-pnpm
../../CLAUDE.md.
api-integration
Frontend API Integration Patterns.