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 instructions/kychee-com/run402-core/agents-mdgit clone --depth 1 https://github.com/kychee-com/run402-coreWhat 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 | $0.00568 | $0.00568 |
| Opus 5 | $0.00284 | $0.00284 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
run402-core AGENTS.md 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions — run402-core
Start with ARCHITECTURE.md and CONTRIBUTING.md for repo orientation; CLOUD_VS_CORE.md explains what belongs here versus the hosted platform.
Git workflow — worktrees, never branches
Multiple agent sessions work these repos in parallel. Isolation is by git worktree (git worktree add), never by switching branches in the main checkout, and never git stash. Push docs-and-small changes directly to main (git push origin HEAD:main, rebase on rejection).
Fleet coordination room — join at session start
Agent sessions working on the run402 codebases (this repo, run402, run402-private) share the coordination room run402-dev on org 57035b1e-ec41-4ce6-a7a5-a5b2560efdd7. Arrive by exporting the address once — then every later room call, including the ones inside skills, is flag-free:
export RUN402_ROOM=57035b1e-ec41-4ce6-a7a5-a5b2560efdd7/run402-dev RUN402_WALLET=platform-deploy
run402 rooms join --name <pick-your-own> --task "<what you're doing>"
run402 messages list --unread
(--wallet platform-deploy applies on machines where another local profile is active; drop it if your session's own wallet is an org member, or set RUN402_ROOM=57035b1e-ec41-4ce6-a7a5-a5b2560efdd7/run402-dev and omit the flags.) Pick your own presence name — collisions get an honest suffix (Opus → Opus-2). Claim shared areas before editing (run402 claims create repo:<area>/** --note "why" — advisory, never blocks; release when done). End your session with an --ack handoff message stating done / hot / next. Tool friction goes to --thread dx. Need a human? Send with --importance high — asking is always in-policy. The .run402/ cache dir this creates is per-checkout and never committed.
Skills announce shared-state work. /publish-core reports the published version and whether the gateway pin is done — npm is irreversible and the private repo's pickup is a second step someone may be waiting on. Best-effort (|| true), so a wedged room can never fail a publish. Reading and thinking skills are deliberately not wired: announcing them is the noise that makes agents stop reading the room.
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.
- 2d ago First seen · 22 lines · 568 tokens per session scan A 2407657e0df1
run402-core AGENTS.md is an instructions file published in the GitHub repository kychee-com/run402-core (20 stars, last pushed 8d ago), licensed Apache-2.0. It adds 568 tokens to every session, about $0.0028 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 2026-08-30.
Other instructions, from other repositories
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
helmor AGENTS.md
Instructions for dohooo/helmor, covering agents.md, what is helmor, commands, architecture and three-process model.
technocore-chat AGENTS.md
Instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
matt-skills-with-to-goal CLAUDE.md
Instructions for tt-a1i/matt-skills-with-to-goal: Skills are organized into bucket folders under skills/.
ephemeral-sandbox CLAUDE.md
Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.
pixir CLAUDE.md
Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.