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/astandrik/codex-pets/agents-mdgit clone --depth 1 https://github.com/astandrik/codex-petsWhat 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 | $0.01914 | $0.01914 |
| Opus 5 | $0.00957 | $0.00957 |
| Sonnet 5 | $0.00383 | $0.00383 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
codex-pets 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Precedence: the closest AGENTS.md to the files you edit wins. Root defines repo-wide defaults.
Commands (verified)
Source:
package.json,tsconfig.json, local verification on 2026-05-09
| Task | Command | ~Time |
|---|---|---|
| Install deps | npm install |
~1m |
| Typecheck | npx tsc --noEmit --incremental false |
~1s |
| Lint | npm run lint |
~1s |
| Test (all) | npm test |
~1s |
| Build | npm run build |
~10s |
| Dev server | npm run dev -- --port 3000 |
~1s startup |
Workflow
- Read nearest
AGENTS.mdbefore editing. - For
src/**, check./src/AGENTS.md. - Run the smallest relevant check after each change.
- Before claiming completion, provide evidence from
lint,test,build, or browser verification.
File Map
src/app/ -> Next App Router pages, layouts, API routes
src/components/ -> UI components with adjacent SCSS
src/components/WebMCP/ -> client-only read-only WebMCP tool registration
src/lib/auth/ -> internal auth helpers and admin checks
src/lib/metrics/ -> Yandex Metrika counter and goal helpers
src/lib/pets/ -> pet types, validation, package parsing, repository logic
src/lib/ydb/ -> YDB driver wrapper, query result parsing, table names
src/styles/ -> global SCSS variables, mixins, utilities, overrides
public/ -> static assets such as favicon
ydb/schema.yql -> manual YDB schema; apply outside the app
README.md -> local setup and stack overview
DEPLOYMENT.md -> production deployment runbook
Golden Samples (follow these patterns)
| For | Reference | Key patterns |
|---|---|---|
| API route flow | src/app/api/submissions/register/route.ts | auth -> config guard -> request parse -> validation -> repository |
| YDB repository | src/lib/pets/repository.ts | keep YQL close to feature logic; return normalized app types |
| Client upload flow | src/components/SubmitForm/SubmitForm.tsx | ZIP/file normalization, client-side atlas checks, explicit server calls |
| Validation helpers | src/lib/pets/validation.ts | typed result unions, boundary checks, no ad hoc parsing in routes |
| WebMCP tool layer | src/components/WebMCP/WebMCPRegistrar.tsx | feature-detect navigator.modelContext; read-only tools; sanitize public pet data |
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 · 127 lines · 1,914 tokens per session scan A 7cb01fa95dc3
codex-pets AGENTS.md is an instructions file published in the GitHub repository astandrik/codex-pets (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,914 tokens to every session, about $0.0096 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 instructions, from other repositories
cezar AGENTS.md
Instructions for open-mercato/cezar, covering agents.md — working in this repository, zero config, changing a mechanism that already works, the http api and repository layout.
trusty-squire CLAUDE.md
Instructions for Trusty-Squire/trusty-squire, covering claude.md, project overview, objective function (what this project optimizes for), current state and production, deployed, verified end-to-end.
hop AGENTS.md
Instructions for amittamari/hop, covering agent map, start here, what this repo builds, working rules and common commands.
libtmux-mcp AGENTS.md
Instructions for tmux-python/libtmux-mcp, covering agents.md, what is here, which policy applies, change discipline and references.
telltale CLAUDE.md
Claude Code instructions for sanlee-ys/telltale, covering telltale — contributor contract, build and test, golden tests: the actual workflow and its traps, a council test never spawns a vendor and commit / pr voice.
hoi4-agent-tools AGENTS.md
Instructions for klimPaskov/hoi4-agent-tools, covering project instructions, engineering boundaries, code and tests and documentation and releases.