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/lukapetro/itaca/agents-mdgit clone --depth 1 https://github.com/Lukapetro/itacaWhat 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 | $0.00219 | $0.00219 |
| Opus 5 | $0.00110 | $0.00110 |
| Sonnet 5 | $0.00044 | $0.00044 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
itaca 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 yesterday.
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
itaca
Local-first registry of a developer's projects, served to coding agents via MCP. The full design is in SPEC.md — read it before structural changes.
Commands
bun test— run tests (detection uses fixture repos + golden files in tests/fixtures/)bun run typecheck/bun run lint— must pass before commit (lefthook enforces)bun run dev— run the CLI locally
Conventions
- Runtime is Bun, TypeScript strict, formatting/linting via Biome (not eslint/prettier).
- Conventional Commits (
feat:,fix:,chore:...); each user-facing change needs a changeset (bunx changeset). Release automation handles versioning and npm publish. - Detector rules are declarative YAML in rules/ (format: SPEC.md §6.1) — never hardcode service detection in TypeScript.
- Hard invariant: values from
.env*files must never be written to any output or file.
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.
- yesterday First seen · 20 lines · 219 tokens per session scan A 7dc584e942d2
itaca AGENTS.md is an instructions file published in the GitHub repository Lukapetro/itaca (0 stars, last pushed 20d ago), licensed MIT. It adds 219 tokens to every session, about $0.0011 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
agents
Always-loaded project anchor. Read this first. Contains project identity, non-negotiables, commands, and pointer to ROUTER.md for full context.
vibe-garden CLAUDE.md
Instructions for rjroy/vibe-garden, covering claude.md, repository overview, repository structure, plugins and compass rose.
repo-continuity CLAUDE.md
Instructions for vector233/repo-continuity, a project described as: Durable, repository-owned project knowledge and lightweight delivery for AI coding agents.
AgentPrecept AGENTS.md
Instructions for rg8diaoa/AgentPrecept, covering agents.md — agentprecept, auto-pilot 模式（默认开启）, 默认行为（无条件执行）, 设计先行原则 and 讨论阶段拦截.
plan42 AGENTS.md
AGENTS.md instructions for sh1nj1/plan42, covering agent development guide, documentation language, documentation index and agent operating rules.
task-cli GEMINI.md
Instructions for sunjiawe/task-cli, covering agentic coding: humans design, agents code!, agentic coding steps, example llm project file structure, pocket flow and core abstraction.