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/inboxapi/cli/agents-mdgit clone --depth 1 https://github.com/inboxapi/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 | $0.00545 | $0.00545 |
| Opus 5 | $0.00272 | $0.00272 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
cli AGENTS.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Never use `execSync` / `execFileSync` with string interpolation — pass arguments as arrays to avoid shell injection How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Agent Stub
Canonical workflow lives in ../AGENTS.md.
Repo-local notes:
- Verification flow:
cargo fmt,cargo clippy -- -D warnings,cargo test,cargo build - This repo owns the CLI binary, npm packaging, and agent-install setup logic
- Canonical service docs live in
../docs/services/cli/ - Never re-create buffered readers (
BufReader) in a loop or per-call; store them in the struct so buffered data is not lost - Use iterators (
iter().take(n)) instead of index-basedfor i in 0..nloops when only indexing a single collection - Add timeouts to any blocking I/O (network, subprocess reads) — tests and tools must not hang indefinitely
- Include descriptive messages in all
assert!/assert_eq!macros
JavaScript / Node.js
- Never use
execSync/execFileSyncwith string interpolation — pass arguments as arrays to avoid shell injection - Do not mark synchronous functions
async— it is misleading and wraps the return in an unnecessary Promise - Handle chunked
dataevents from child process stdout with line-based parsing (e.g.readline.createInterface), not rawJSON.parseon each chunk - When communicating with a subprocess over its lifetime, spawn it once and reuse the connection — do not spawn a new process per request
- Validate all user input (bounds checks, type checks) before using it to index arrays or build commands
- Centralize model identifiers in a single constant or environment variable; avoid scattering hardcoded dated model version strings throughout the code
MCP Protocol
- After sending
initialize, always sendnotifications/initializedbefore any other requests — skipping this violates the MCP handshake and may cause server rejection
Pre-completion Checklist
Before declaring work done, run these in order:
cargo fmt— format codecargo clippy -- -D warnings— lint with zero warningscargo test— all unit tests passcargo build— clean compilation- Test each new CLI subcommand — after building, run each new or modified subcommand against the live API to verify it works end-to-end (e.g.
cargo run -- get-emails --limit 3 --human)
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 · 40 lines · 545 tokens per session scan A f368cc4f5e4a
cli AGENTS.md is an instructions file published in the GitHub repository inboxapi/cli (12 stars, last pushed 2mo ago), licensed MIT. It adds 545 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
postmark-mcp CLAUDE.md
Instructions for ActiveCampaign/postmark-mcp, covering claude.md, project overview, commands, architecture and mcp tools registered.
email-templates CLAUDE.md
Instructions for ColorlibHQ/email-templates, covering claude.md, repository purpose, layout, commands and editing or adding a template.
mcp-dotnet-samples AGENTS.md
Instructions for microsoft/mcp-dotnet-samples, covering agents.md - mcp .net samples, project overview, project structure and architecture, repository organization and sample components.
Embody AGENTS.md
Instructions for dylanroscover/Embody, covering embody + envoy - ai instructions, critical rules, td python rules, network layout rules and mcp server safety rules.
cli AGENTS.md
Instructions for nylas/cli, covering ai coding agent guidelines, quick reference: shared helpers, quick reference: adding a new feature and quick reference: credential storage.
better-email-mcp CLAUDE.md
Instructions for n24q02m/better-email-mcp, covering claude.md - better-email-mcp, commands, setup, lint & type check and fix.