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/viethann/agent-workspace/agents-mdgit clone --depth 1 https://github.com/VietHann/agent-workspaceWhat 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 | $0.00493 | $0.00493 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
agent-workspace 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This is a single TypeScript package, not a monorepo. src/analyzer/ collects repository evidence into ProjectContext; src/catalog/ loads and validates repository-owned YAML; src/generator.ts creates canonical files and owns safe writes; and src/adapters/ translates the manifest into vendor entry points without writing directly. src/commands.ts exposes reusable command operations, while src/cli.ts contains terminal presentation.
Built-in definitions live in agents/*.yaml and skills/<name>/skill.yaml. Keep these as data rather than embedding their content in TypeScript. templates/ is the contribution starting surface. examples/next-supabase/ is both a representative fixture and a checked-in generated workspace. Tests in tests/ cover schemas, analysis, generation, and real CLI execution.
Build, Test, and Development Commands
pnpm dev -- <command>runs the source CLI, for examplepnpm dev -- analyze ..pnpm typecheckruns strict TypeScript checking without emitting files.pnpm testruns all Vitest tests once.pnpm vitest run tests/analyzer.test.tsruns one test file.pnpm validatevalidates catalog schemas, type-checks, and runs tests.pnpm buildbundles ESM executables and declarations intodist/with tsup.
Coding Style & Naming Conventions
TypeScript uses strict mode, NodeNext modules, two-space indentation, and explicit .js suffixes in source imports. Extension names and workflow IDs are lowercase kebab-case; extension versions are semantic versions. Zod schemas are strict, so public format changes require deliberate schema and fixture updates. Preserve deterministic sorting in analysis and generation. All writes must remain inside the target repository and must preserve conflicts unless the caller selects force.
Testing Guidelines
Vitest runs in the Node environment. Use temporary directories from tests/helpers.ts for filesystem behavior and clean them after each test. Test both observable files and parsed schemas. CLI behavior changes require a child-process test, not only direct function coverage.
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 · 29 lines · 493 tokens per session scan A dd09d9837978
agent-workspace AGENTS.md is an instructions file published in the GitHub repository VietHann/agent-workspace (4 stars, last pushed 2d ago), licensed MIT. It adds 493 tokens to every session, about $0.0025 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
meta-llm-charter CLAUDE.md
Instructions for entropyvortex/meta-llm-charter, covering meta v3.1 core charter, bias, meta-0, r1 decompose and r2 ask gate.
awesome-reviewers CLAUDE.md
Instructions for baz-scm/awesome-reviewers, covering awesome reviewers — repository guidelines, what this project is, source of truth, site layer and machine interface.
code-context AGENTS.md
Instructions for infino-ai/code-context, covering code-context: notes for ai agents, project overview, repo map, build, test, gates and conventions.
gtm-cheat-codes CLAUDE.md
Instructions for zapier/gtm-cheat-codes, covering repo conventions and commits.
Stata-CLI AGENTS.md
Instructions for Utolaris/Stata-CLI, covering agents.md, project structure and working rules.
waybill AGENTS.md
Instructions for wardmos/waybill, covering agents.md, privacy, checks, commit messages and git history.