atet: Instructions file for Codex

AGENTS.md

atet AGENTS.md is an instructions file for Codex, OpenCode from hraness/atet. It costs 3,210 tokens per session, scanned A, original, MIT.

Repository instructions for atet, a local-first toolkit for AI media generation and video editing used by coding agents. They describe the project structure, workflows, diagrams, desktop and web applications, and knowledge base.

In plain words
What is it for?
They help agents work on atet's TypeScript and Bun tools, media workflows, desktop application, web site, scene analysis, diagrams, and documentation.
Why use it?
They give agents the project-specific context needed to navigate the codebase and follow its conventions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; mentions AGENTS.md; $skill-name invocation.

This is hraness/atet's own configuration. It tells Codex and OpenCode how to work on atet itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything atet configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hraness/atet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hraness/atet/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/hraness/atet

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for atet AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hraness/atet/agents-md/github.svg)](https://agentmods.dev/instructions/hraness/atet/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hraness/atet/agents-md"><img src="https://agentmods.dev/badge/instructions/hraness/atet/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for atet AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hraness/atet/agents-md"><img src="https://agentmods.dev/badge/instructions/hraness/atet/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,210 This file is loaded in full into every session.
When invoked 3,210 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03210 $0.03210
Opus 5.5 $0.01284 $0.01284
Sonnet 5.5 $0.00642 $0.00642
Haiku 4.5 $0.00321 $0.00321

Measured 2mo ago against content hash 52b4899de0fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

atet 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 2mo 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.

AGENTS.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contents

  • src/ – portable declarative and imperative workflow SDKs, host-resource admission, diagrams, direct Vercel AI Gateway generation, local vectorization, semantic operations, MCP, and canvas integration.
  • apps/desktop/ – the canonical atet CLI, complete local media host, durable scheduler, HTML and Three.js overlays, native capture helpers, frontend, and desktop shell.
  • apps/web/ – the static atet.sh site, with a local browser bundle and a production-only anonymous pageview boundary but no API, account, or credential surface.
  • packages/scene/ – the shared local scene-analysis contract.
  • src/code/ – portable declarative graph authoring, the closed public capability projection, compilation, planning, and execution contracts.
  • schema/ – version-one diagram JSON Schema.
  • skills/atet/ – the canonical Atet Agent Skill.
  • .agents/skills/ – portable repository orchestration and knowledge-base workflows.
  • kb/ – the Git-backed Markdown vault for rationale, evidence, maintained synthesis, plans, and scoped agent context.
  • examples/ – checked diagram, configuration, and executable imperative and declarative Bun workflow examples.
  • scripts/ – schema, skill, package, release, and official-vectorizer verification.
  • dist/ and apps/desktop/dist/cli/ – committed Bun-targeted entrypoints consumed by package and Git installs.
  • .github/workflows/ – routed SDK, local-host, static-site, macOS-native, official VTracer, and immutable release checks.
  • docs/ – current architecture, npm publication, and Vercel provider runbooks.
  • README.md, CONTRIBUTING.md, SECURITY.md, LICENSE, and NOTICE.md – public documentation, policy, and terms.
  • WRITING.md and STYLE.md – internal and public prose contracts.
  • package.json, tsconfig.json, and bun.lock – standalone package and verification configuration.

Guidelines

  • Use Bun 1.3.14 and run bun run check before handing off a change.
  • Follow WRITING.md for internal prose and STYLE.md for public prose, preserving facts, exact terms, literals, quotations, links, and necessary uncertainty.
  • Follow the shared README guidelines for the root README and any site copy that summarizes it.
  • Apply unreasonably robust programming when agent work is cheap. Prefer coherent cross-file correctness and focused deterministic evidence while treating production risk, provider coordination, rollout, and observation as real costs.
  • Deliver changes to main through a current-head pull request. Keep the stable Required CI job green, resolve every review thread, and serialize merges. Human approval stays optional while one regular maintainer would otherwise self-review. Never force-push or bypass the gate.
  • Keep this repository independently buildable. Never depend on sibling paths, Git submodules, or coordinated main branches; consume external Hraness packages only through reviewed immutable release tags or commits.
  • Extract a shared package only after a second concrete consumer proves a stable product-neutral contract. Shared packages never import product code.
  • Keep Atet's product and editor presentation local. Add @hraness/ui for portable accessible primitives or @hraness/design-kit for optional shared presentation only after concrete reuse warrants the dependency; domain layout and content remain Atet-owned.
  • Freeze shared interfaces before parallel lanes begin. Give one integration owner manifests, lockfiles, generated registries, and other convergence files, then let consumers upgrade immutable releases independently.
  • Keep mandatory edit-time rules in the closest AGENTS.md, current procedures in docs/, executable contracts in types, schemas, and tests, and rationale, evidence, synthesis, and plans in kb/. KB lanes run bun run kb:check:lane; the integrator performs one refresh and bun run kb:check.
  • Keep @hraness/atet at the repository root. The root package owns both the portable SDK and canonical atet binary built from apps/desktop/cli/main.ts.
  • Keep canonical commands namespaced as atet diagram init|check|render, atet image generate|vectorize, and the code, mcp, canvas, skill, and doctor surfaces.
  • Keep local vectorization authentication-free and network-silent. Gateway generation reads AI_GATEWAY_API_KEY before VERCEL_OIDC_TOKEN, never persists credentials, pins the Gateway origin, bounds responses, and sets maxRetries: 0.
  • Keep /artifacts/, .env, and .env.* ignored. Recordings, imported media, private project metadata, Gateway tokens, and provider options must never enter Git or a package artifact.
  • Treat vercel env run -- <command> as the ergonomic local Vercel path. Never shell out to infer or scrape a token from the Vercel CLI.
  • Treat Production as Atet's only durable Vercel environment. Do not create a custom environment, persistent Preview domain, or provider-authoritative Preview branch. Pull requests may use Vercel's built-in disposable Preview target, without production-only variables or another durable backend. Follow the Vercel runbook and audit provider identity before changing this seam.
  • Preserve .diagram.json version one and the five same-stem render outputs: .tldr, light and dark SVG, and light and dark PNG.
  • Keep one self-contained Atet identity. Public APIs, serialized identifiers, source imports, configuration, and runtime surfaces use only Atet names.
  • Preserve every immutable version-1 tag and Release. Never rewrite a historical tag or recreate a repository at the former GitHub path, because doing so would replace GitHub's compatibility redirect.
  • Treat diagram source as authoritative and generated media as replaceable. Defaults may resolve mechanics but must not invent claims, labels, legends, relationships, or decorative meaning.
  • Model invalid states out, parse foreign values from unknown, and keep output deterministic. Preserve readable regression examples; add property tests for laws, parsers, reducers, ordering, and round trips, and promote shrunk failures into named deterministic examples.
  • Keep semantic registries fixed and typed. Never accept source text, evaluation, dynamic imports, executable workspace configuration, shell commands, or caller-selected remote URLs.
  • Preserve the root module and ./workflow v0.8 imperative APIs. Add declarative graphs through ./code and lower-level compiler contracts through ./code/advanced; do not add ./code/testing or ./code/workflows exports.
  • Treat explicitly imported workflow modules as trusted current-user Bun code. Compile graphs only against the host's closed capability projection, reject an unsupported capability before executor or resource admission, and do not add an open operation-registration hook.
  • Treat the portable SDK and core as the canonical graph contract. The complete local host consumes that contract through its own closed projection and owns durable media execution. The Desktop shell adds only native capture, permissions, and UI.
  • Model one project as immutable source plus explicit revisions, candidates, selections, and delivery variants. Keep ready work bounded by resource claims and serialize expensive encodes by default.
  • Keep imperative workflows as explicitly imported trusted Bun modules over the fixed operation registry. Parse runtime input, bound and uniquely identify steps, drain dispatched work before returning, retain completed-step receipts on every failure path, and do not load caller-selected source paths.
  • Keep semantic SDK, CLI, MCP, and workflow resource admission machine-global and crash-safe on macOS and Linux, with a truthful process-local fallback elsewhere. Preserve profile identity, FIFO admission for overlapping claims, callback-settlement ownership, and inherited lease descriptors through spawned vectorizer processes.
  • Keep MCP paths root-relative and capability-small. Bound source bytes, arrays, shapes, edges, scale, pixels, findings, subprocess duration, and output bytes before execution.
  • Keep vectorization fail-closed with checksum-pinned VTracer archives, inert rebuilt SVG, measured fidelity, and full provenance receipts. Do not add an embedded-raster fallback, upscaling model, or bundled commercial font.
  • Follow docs/publishing.md for the historical bootstrap and later releases. Preserve contentPolicy.class=dual-use and the root DISCLOSURE in every package. Trust only .github/workflows/npm-stage.yml with npm stage publish permission bound to the exact npm-stage environment. Keep that environment restricted solely to selected main, with administrator bypass disabled, no required deployment reviewers, and no secrets. Pushes and default dispatches build and upload without OIDC; only an owner current-main dispatch with boolean publish_to_npm=true may admit the staging job, which must reauthorize the exact run attempt, owner actor and triggering_actor, workflow/repository identity, protected ref, and source before npm setup. The packed manifest must not contain npm's top-level tag override, and publishConfig must contain exactly canonical public access and registry; independently parse the exact USTAR archive and reject every scoped-registry, proxy, authentication, tag, provenance, or other packed npm override in the OIDC job. Keep the source/release and checkout-free tar readers aligned on the exact eight-byte USTAR signature and byte-475 130/155 prefix semantics, with shared hostile fixtures. Stage only a stable candidate newer than live public latest; use empty user/global npm configuration, reject ambient npm_config_tag, prove pinned npm's untouched default tag is latest, and do not pass --tag so npm's built-in monotonic-latest guard remains active. npm supports multiple pending stages, exposes no atomic single-pending option, and does not authorize npm stage list with the short-lived trusted-publishing token. Keep this workflow the sole staging authority: serialize dispatches, inspect recognized terminal mutation steps before any stage-job display-name filter, record a successful version-bound Actions intent immediately before each mutation attempt, require every attempted terminal write to have exactly one successful durable intent at the immediately preceding safe positive Actions step number, and reject unresolved intents across every retained attempt of the current and completed runs while their version remains newer than public latest. A failed, ambiguous, or rejected stage attempt may release only its exact intent through the exceptional owner-authorized resolved_stage_version input after its provider state is resolved; a promoted stage advances latest and releases its intent automatically. Leave the input empty normally. The one-pending-stage rule is an operational invariant for this authority, not a claim that npm prevents or exposes out-of-band concurrent stages to OIDC. Disallow traditional publishing tokens. npm's public promotion remains human-gated by two-factor authentication.
  • Use two exact active rulesets matching refs/tags/v*: Immutable version tags restricts update and deletion with an empty bypass list, while Release tag creation restricts creation and has owner User ID 894119 as its sole always-bypass actor. Never grant generic GitHub Actions integration ID 15368, an administrator, a repository role, a team, or another integration this bypass; never combine creation with update/delete or create probe tags. Publish and verify the exact staged npm artifact first, approve its public promotion with human 2FA, then run bun run ./scripts/push-npm-release-tag.ts <exact-stable-version> from clean current main; that preflight-only creator must read back owner/repository/rulesets/environment/protected-main/CI/public-latest/remote-tag identity before its sole exact annotated-tag push and must never publish npm. The protected tag workflow must bind actor and event sender to owner User ID 894119 and repository ID 1310516748 before checkout, require exact public dist-tags.latest, registry signatures, and npm-audit-verified npm-publish plus SLSA attestations bound to the tarball, source SHA, npm-stage.yml on main, workflow_dispatch, repository and owner IDs, GitHub-hosted builder, and signed stage run attempt. Immediately before the immutable Latest Release, re-read that exact owner-triggered attempt and its version-bound job, require one successful durable intent directly before the attempted npm mutation, and re-read live npm latest, integrity, signatures, and attestations. Do not require whole-job success: a failed, cancelled, or timed-out runner may have completed the provider write, and the exact cryptographically verified public provenance is the durable acceptance proof. Bind the Release body to the exact workflow, repository, tag, source, stage attempt, integrity, and attestation; accept an existing Release only from GitHub Actions bot ID 41898282 with that exact provenance and title. Never move a tag or republish an npm version.

Read the full file on GitHub · 67 lines

Changes

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.

  1. 2mo ago Changed · +499 tokens per session 52b4899de0fe
  2. 2mo ago Changed · +11 lines · +762 tokens per session c2d11166dc61
  3. 2mo ago First seen · 56 lines · 1,949 tokens per session scan A 89d87c747cb6

Subscribe to this mod's changes

atet AGENTS.md is an instructions file published in the GitHub repository hraness/atet (5 stars, last pushed 1mo ago), licensed MIT. It adds 3,210 tokens to every session, about $0.0128 per session on Opus 5.5. 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.

Related

atet AGENTS.md compared with instructions from other repositories

atet AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
atet AGENTS.mdhraness/atetInstructions file51mo agoMITA3,210Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode