Borrowing it
Nothing to install: this file belongs to williamhallatt/cogworks. 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/williamhallatt/cogworks/main/AGENTS.mdgit clone --depth 1 https://github.com/williamhallatt/cogworksWrote 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/williamhallatt/cogworks/agents-md)<a href="https://agentmods.dev/instructions/williamhallatt/cogworks/agents-md"><img src="https://agentmods.dev/badge/instructions/williamhallatt/cogworks/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.
<a href="https://agentmods.dev/instructions/williamhallatt/cogworks/agents-md"><img src="https://agentmods.dev/badge/instructions/williamhallatt/cogworks/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00387 | $0.00387 |
| Opus 5.5 | $0.00155 | $0.00155 |
| Sonnet 5.5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
cogworks 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.
What it actually says
Repository Guidelines
What this repo is
Two advisor skills for authoring agent skills:
skills/cg-distill/— synthesis methodology: turn one or more sources on a topic into a decision-first knowledge baseskills/cg-build/— skill-authoring doctrine: structure, package, and validate an agent skill for its target runtime
Both work standalone. Install with npx skills add williamhallatt/cogworks. See README.md.
Project structure
skills/cg-distill/,skills/cg-build/— canonical skill sources; edit here directly_sources/— research material (Agent Skills spec + docs snapshot from agentskills.io); do not auto-load, consult only when a task explicitly calls for reference material
Live-edit hazard
Editing a SKILL.md while operating under that skill's instructions puts the session in a circular / inconsistent state. When editing any skills/cg-*/SKILL.md, don't invoke that skill during the session. If you invoke a skill you're editing by accident, restart or verify the in-memory instructions still match the current file.
Coding style
- Skill directories and slugs use kebab-case
SKILL.mdfrontmatter is valid YAML with requiredname:anddescription:fields
Git
- Commit format:
<type>/ <summary>—add/,fix/,refactor/,docs/,chore/,release/ - Stage explicit paths, not
git add . - Never touch
.env - Never run destructive git operations (
git reset --hard,git push --force, tag deletion of published tags,git checkoutto an older commit) without an explicit written instruction from the user in the current conversation - Never amend commits without explicit approval
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.
- 2mo ago Changed · -7 tokens per session a85ea3009715
- 2mo ago First seen · 33 lines · 394 tokens per session scan A c685ba650f41
cogworks AGENTS.md is an instructions file published in the GitHub repository williamhallatt/cogworks (5 stars, last pushed 1mo ago), licensed MIT. It adds 387 tokens to every session, about $0.0015 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.
cogworks AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cogworks AGENTS.mdwilliamhallatt/cogworks | Instructions file | 5 | 1mo ago | MIT | A | 387 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |