Borrowing it
Nothing to install: this file belongs to elliottdehn/wam. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/elliottdehn/wam/main/AGENTS.mdgit clone --depth 1 https://github.com/elliottdehn/wamWrote 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.
[](https://agentmods.dev/instructions/elliottdehn/wam/agents-md)<a href="https://agentmods.dev/instructions/elliottdehn/wam/agents-md"><img src="https://agentmods.dev/badge/instructions/elliottdehn/wam/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00597 | $0.00597 |
| Opus 5 | $0.00298 | $0.00298 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
wam 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 8d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WAM repository guidance
Use .agents/skills/wam/SKILL.md for character, creature, prop, rig,
animation, reference-image, or .wam work.
Local setup
- On Windows, run
powershell -ExecutionPolicy Bypass -File .\Setup-WAM.ps1. On macOS and Linux, run./setup-wam.sh. Both create the same.venv. - Use that virtual environment's interpreter explicitly afterwards:
.\.venv\Scripts\python.exeon Windows,./.venv/bin/python3on macOS and Linux. Do not depend on whichever interpreter is first onPATH. - Commands below are written
python3, which resolves on macOS and Linux both inside and outside the venv. Windows has nopython3: use.\.venv\Scripts\python.exeorpy -3there. - Use
python3 -m wam.codex_clifor agent work because it reserves stdout for deterministic JSON.python3 -m wam.cliremains the human-oriented command.
Multi-image and multi-view contract
- Prepare every supplied reference with
wam.codex_cli references; keep whole-object views, detail images, and palette images as separate named evidence. - Read every entry and crop group in
references.json; do not summarize all references from a single contact sheet. - Compile with all relevant named or custom views. Read
_views.json, then inspect every listed PNG individually before judging the combined sheet. - Unknown, empty, and duplicate view names are errors. Custom views use
id:yaw[:pitch]in degrees. - Preserve the historical
.gltf, viewer HTML, and sheet outputs when changing render behavior.
Colour
- Colours are authored as sRGB hex and held internally as linear;
wam/color.pyowns both conversions and is the only module that should. - Colour enters through
parser._hex_color(andedits._color) and leaves throughrender.write_png/png_bytes. A new consumer that wants sRGB encodes at its own edge; a new exporter that wants linear writes the value it already has. tests/test_colorspace.pyholds the guarantee that whatever hex an author writes is what an importer receives.
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.
- 8d ago First seen · 52 lines · 597 tokens per session scan A deb80ee9f309
wam AGENTS.md is an instructions file published in the GitHub repository elliottdehn/wam (54 stars, last pushed 15d ago), licensed MIT. It adds 597 tokens to every session, about $0.0030 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.