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/tutur3u/platform/agents-mdgit clone --depth 1 https://github.com/tutur3u/platformWhat 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 | $0.04703 | $0.04703 |
| Opus 5 | $0.02351 | $0.02351 |
| Sonnet 5 | $0.00941 | $0.00941 |
| Haiku 4.5 | $0.00470 | $0.00470 |
Grade A, and why
platform 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 3d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Operating Manual For Autonomous AI Assistants
1. Authority
Foundational mandates here take absolute precedence. Never invent ad-hoc
behavior. This file is the hard-policy index for the Tuturuuu platform
monorepo; detailed reusable patterns live in the repo-local Tuturuuu Codex
plugin under plugins/tuturuuu/skills/*/references/ and in apps/docs.
Read the nearest AGENTS.md first, then load the focused Tuturuuu skill for the
surface you are changing:
$tuturuuu-platformfor generalapps/web, shared packages, translations, navigation, docs, and repo verification.$tuturuuu-web-releasefor version badge, release metadata,TUTURUUU_PLATFORM_VERSION, or blue/green release snapshot work.$tuturuuu-agent-coordinationfor dirty/shared worktrees, handoffs, staged path safety, coordination notes, and commit-window coordination.$tuturuuu-development-toolingfor plugin skills, validation scripts, root scripts, CI, and durable agent workflow improvements.$tuturuuu-databasefor Supabase migrations, RLS, protected-table API writes, storage policy, generated DB types, and database aliases.$tuturuuu-ci-docsfor GitHub Actions,tuturuuu.ts, validators, docs pages, docs navigation, and Docker deployment runbooks.$tuturuuu-mobile-task-boardfor Flutter mobile task-board behavior and mobile release metadata follow-through.$tuturuuu-cli,$tuturuuu-cli-tasks, and$tuturuuu-cli-financefor nativettrworkflows.$tuturuuu-commitfor explicit commit/commit-and-push requests.$tuturuuu-review-commentsfor GitHub PR review-thread follow-through.$tuturuuu-pr-merge-syncfor PR quiet-window merge follow-through, mandatory main-green verification,bun git-sync, and production-green verification.
2. Hard Prohibitions
- Do not run long-running or build/bundling commands such as
bun dev,bun run build,bun build, or equivalents unless the user explicitly asks. - Do not run
bun sb:pushorbun sb:linkpush; prepare migrations and let the user apply production Supabase changes. - Do not commit secrets, API keys, tokens, credentials, or raw sensitive values. Reference environment variables by name only.
- Do not manually edit
package.jsonto add or update dependencies. Use the package manager command for the owning workspace. - Do not use native browser dialogs, emojis in UI code, hard-coded hue classes,
client-side raw app API fetches, or
useEffectfor data fetching. - Do not add
export const dynamic/export const revalidateroute segment configs. Every Next app runs withcacheComponentsenabled, which rejects them at build time. Opt an authed page or Supabase-backed GET route handler into request-time rendering withawait connection()instead (see$tuturuuu-platform→ Cache Components). - Do not resolve actors in a registered satellite app with
@tuturuuu/utils/user-helper(getCurrentUser,getCurrentWorkspaceUser) — those read Supabase auth directly. UsegetSatelliteAppSessionUser('<app>')and pass the id into an injectable helper (e.g.@tuturuuu/utils/workspace-user-link).bun checkenforces this via theinternal-app-authguard. - Do not add a catch-all page (
[...slug]) under[locale]/[wsId]in a satellite that proxies/api/*to web. Next checksfallbackrewrites only AFTER dynamic routes, so the catch-all swallows/api/v1/...aslocale="api",wsId="v1"and breaks every proxied API call. Put non-migrated-route redirects in the app'sproxy.tsmiddleware instead. - Use native
console.*for server runtime logs, preserving severity (console.error,console.warn, etc.). Do not addserverLoggerruntime imports or automatic console log-drain installation. - Do not modify, format, stage, commit, delete, rename, or clean up files you did not intentionally touch.
- Do not use destructive Git or filesystem commands unless the user clearly asks for that operation and the scope is explicit, except for the narrowly scoped post-merge worktree and local task-branch cleanup mandated below.
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.
- 3d ago First seen · 337 lines · 4,703 tokens per session scan A 9f913b06d7f4
platform AGENTS.md is an instructions file published in the GitHub repository tutur3u/platform (53 stars, last pushed 3d ago), licensed Apache-2.0. It adds 4,703 tokens to every session, about $0.0235 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
magicui AGENTS.md
Instructions for magicuidesign/magicui, covering project context, key principles, before writing code, rules and accessibility (a11y).
kan AGENTS.md
AGENTS.md instructions for kanbn/kan, covering agents.md, project overview, setup commands, project structure and code style.
coss AGENTS.md
AGENTS.md instructions for cosscom/coss, covering agents.md and main documentation.
ui-beats AGENTS.md
Instructions for nikhils4/ui-beats: This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in nodemodules/next/dist/docs/ (resolved from this file's directory; in monorepos the next package may not be visible from the repo root) before…
cali.so AGENTS.md
AGENTS.md instructions for CaliCastle/cali.so, covering cali.so, agent skills, issue tracker, triage labels and design.
cali.so CLAUDE.md
Claude Code instructions for CaliCastle/cali.so, a project described as: Personal website for Cali Castle.