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/codee-sh/payload-training-app/agents-mdgit clone --depth 1 https://github.com/codee-sh/payload-training-appWhat 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 | $0.02494 | $0.02494 |
| Opus 5 | $0.01247 | $0.01247 |
| Sonnet 5 | $0.00499 | $0.00499 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
payload-training-app 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Operational guide for AI agents working in this repository.
Before Writing Code
- Write everything in English: code, comments, variable names, documentation.
- Do not implement code, schema, migration, script, configuration, or documentation changes unless the user explicitly authorizes implementation with "wdrażamy" or an equivalent clear instruction. Analysis, investigation, and recommendations do not authorize changes.
- Check
.ai/specs/before coding any non-trivial feature. - Skills are installed in
.claude/skills/(Claude Code) and.agents/skills/(Codex)..agents/skills/is the local source of truth — edit a skill only there, then runags push-skillto propagate it to the source repo (it also syncs the.claude/skills/copy). See Installing skills. - Prefer minimal, focused changes. Do not refactor code outside the task scope.
- Do not run
yarn buildautomatically after implementation. Run it only when the user explicitly asks. - Comment and naming conventions are defined in the
code-styleskill. Load it before writing or reviewing TypeScript.
Task Router
Match the task to the table before starting. A single task often maps to multiple rows.
| Task | Action |
|---|---|
| Creating a new collection or extending the schema | Load skill payload-build-collections |
| Adding a custom admin view, tab, or field UI | Load skill payload-build-modules |
Building a front-end component or page (src/components, src/modules/*/components, (frontend)) |
Load skill payload-frontend-build-components |
| Debugging hooks, queries, access control, transactions | Load skill payload |
| Security review, or adding/modifying auth, access control, uploads, CORS/CSRF, headers | Load skill payload-security; keep .ai/audits/security-audit.md current |
| Writing questions for a client or stakeholder | Load skill writing-questions |
| Starting a new spec or reviewing one | Load skill spec-writing |
| Any TypeScript code | Load skill code-style |
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 · 211 lines · 2,494 tokens per session scan A dcd1b8885b1b
payload-training-app AGENTS.md is an instructions file published in the GitHub repository codee-sh/payload-training-app (11 stars, last pushed 20d ago), licensed MIT. It adds 2,494 tokens to every session, about $0.0125 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).
core CLAUDE.md
Claude Code instructions for module-federation/core, covering claude task parallelization & development guidelines, core principles, maximum parallelization strategy, universal parallel task patterns and for any codebase task.
intlayer CLAUDE.md
Instructions for aymericzip/intlayer, covering repo layout, commands (run from root), content declaration flow, git and commit conventions.
postiz-app copilot-instructions.md
Copilot instructions for gitroomhq/postiz-app, covering copilot coding agent instructions for postiz, project architecture, developer workflows, conventions & patterns and integration points.
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…
riffpad AGENTS.md
Instructions for riffpad/riffpad, covering riffpad agent guide, project, rules, conventions and done means.