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/lizard-build/lizard-cli/agents-mdgit clone --depth 1 https://github.com/lizard-build/lizard-cliWhat 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 | $0.01444 | $0.01444 |
| Opus 5 | $0.00722 | $0.00722 |
| Sonnet 5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00144 | $0.00144 |
Grade A, and why
lizard-cli 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working in this repo (@lizard-build/cli).
Package manager
This project uses npm. Don't introduce pnpm/yarn lockfiles. Scripts:
npm run build— TypeScript compile todist/npm run dev— run from source viatsxnpm test— integration tests (test/cli.test.ts)npm run test:unit— unit tests (test/unit/*)
The published bin is dist/index.js. Always run npm run build before testing against dist/.
Project layout
src/
index.ts # Commander root, banner, preAction (auth + JSON mode), --help --json dump
commands/<name>.ts # one file per top-level command; exports register<Name>(program)
lib/
api.ts # fetch wrapper, APIError
auth.ts # token store, requireAuth()
config.ts # ~/.lizard/config.json read/write
format.ts # printJSON, isJSONMode, success/error/info/warn, table, statusColor
picker.ts # interactive @clack pickers
resolve.ts # resolve workspace/project/service from flags or linked dir
updater.ts # self-update (precompiled binary only — see note below)
skill-data/<name>/SKILL.md # agent skills served by `lizard skill get <name>`
dist/ # tsc output, committed; this is what npm ships
test/cli.test.ts # integration tests (spawn the CLI)
test/unit/*.test.ts # unit tests
Code style
- Kebab-case for CLI flags (
--service-name, never--serviceName). - No emojis in code, output, or docs. Unicode glyphs (
✓,✗,→) viachalkare fine. - Colors: use
chalkandlib/format.tshelpers. Never hardcode ANSI escapes. info/success/warn/errorwrite to stderr; payload (printJSON, table rows) goes to stdout. Pipes (| jq,> file) must work.- Strict TypeScript. No
anyin new code unless interacting withcommander's loose types.
JSON mode is required
Every user-facing command must support --json. The harness in src/index.ts auto-enables it when stdout isn't a TTY, and lib/format.ts gates pretty prints. Pattern:
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 · 114 lines · 1,444 tokens per session scan A 464089244890
lizard-cli AGENTS.md is an instructions file published in the GitHub repository lizard-build/lizard-cli (2 stars, last pushed 4d ago), licensed MIT. It adds 1,444 tokens to every session, about $0.0072 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
defang AGENTS.md
Instructions for DefangLabs/defang, covering defang cli agent guide, repository basics, common commands, agent enforcement and go change quality.
defang CLAUDE.md
Instructions for DefangLabs/defang, a project described as: Defang CLI. Develop Once, Deploy Anywhere. Take your app from Docker Compose to a secure and scalable deployment on your favorite cloud in minutes.
atmos CLAUDE.md
Claude Code instructions for cloudposse/atmos, covering claude.md, project overview, git worktrees (mandatory), concurrent sessions (mandatory) and hourly pr maintenance loop (recommended).
stackql AGENTS.md
Instructions for stackql/stackql, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
cloudinary_npm AGENTS.md
Instructions for cloudinary/cloudinary_npm, covering contributor guide for coding agents, commands, testing, project structure and code style.
mcp-ssh-manager CLAUDE.md
Instructions for bvisible/mcp-ssh-manager, covering claude.md, project overview, architecture, commands and setup and installation.