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/antonlunden/inkdex/agents-mdgit clone --depth 1 https://github.com/antonlunden/inkdexWhat 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 | $0.00405 | $0.00405 |
| Opus 5 | $0.00202 | $0.00202 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
inkdex 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.
What it actually says
AGENTS.md
- Use Conventional Commits (
feat:,fix:,chore:,docs:)
General Coding Guidelines
- Maintain consistency with existing patterns and style in the codebase
- Use TypeScript strictly: enable
strict: true, preferunknownoverany, avoid type assertions unless necessary - Write comments that explain why, not what—update or remove stale comments when modifying code
- Prefer renaming over commenting: if code needs a comment to explain what it does, rename instead
- Use JSDoc (
/** */) only for exported functions/types; use//for implementation notes - Use
@packageon exports internal to their feature package - Include
@examplein JSDoc when input/output isn't obvious from the signature - No commented-out code, no TODO/FIXME without a linked issue
- Naming: camelCase functions/variables, PascalCase types/classes, UPPER_SNAKE_CASE constants; prefix booleans with
is/has/should - Keep functions focused and single-responsibility; favor immutable patterns (
readonly, no mutation) - Handle errors consistently: prefer typed errors or Result patterns, handle promise rejections explicitly
- Use modern syntax: optional chaining (
?.), nullish coalescing (??),satisfies, ES modules - After refactoring, run
npm run testto verify tests pass and coverage requirements are met - Write tests covering happy path, edge cases, and error conditions with descriptive names
- Test should validate observable behavior not implementation details
Development
npm install
npm run build # TypeScript compilation
npm run dev # Run via tsx
npm run check # Biome lint
npm run format # Biome format
npm test # Unit + integration
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 · 33 lines · 405 tokens per session scan A b0b1dd9604cd
inkdex AGENTS.md is an instructions file published in the GitHub repository antonlunden/inkdex (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 405 tokens to every session, about $0.0020 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
mcp-plesk-dev-docs copilot-instructions.md
Instructions for barateza/mcp-plesk-dev-docs, covering plesk unified mcp server - ai agent instructions, project overview, architecture & components, core stack and data flow.
agentdocs-mcp CLAUDE.md
Claude Code instructions for hoornet/agentdocs-mcp, covering claude.md, what this is, layout, two invariants that have each caused a shipped bug and releasing.
notion-mcp CLAUDE.md
Instructions for shck-dev/notion-mcp, covering notion mcp server, package, architecture, auth and tools.
lightpaper CLAUDE.md
Claude Code instructions for lightpaperorg/lightpaper, covering lightpaper.org — claude code instructions, architecture, key files, running locally and running tests.
lightpaper AGENTS.md
AGENTS.md instructions for lightpaperorg/lightpaper, covering agents.md — lightpaper.org, what is lightpaper.org?, quick start, mcp server (recommended for agents) and direct api.
precis-mcp AGENTS.md
AGENTS.md instructions for retospect/precis-mcp, covering precis-mcp — agent context, identity, stack / toolkit, repository shape and workflow — plan first, always.