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/hafeok/product-cli/claude-mdgit clone --depth 1 https://github.com/Hafeok/product-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 | $0.08401 | $0.08401 |
| Opus 5 | $0.04201 | $0.04201 |
| Sonnet 5 | $0.01680 | $0.01680 |
| Haiku 4.5 | $0.00840 | $0.00840 |
Grade A, and why
product-cli CLAUDE.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 — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Product CLI
What is this project?
Product is a Rust CLI and MCP server for the Product Framework — the open
What/How specification graph (docs/product-framework-open.md, currently
v1.9.1). It captures and verifies a product's What (domain model, event model,
Deciders, Projectors, systems, triggers, UI/AIO model) and How (contracts,
reification, delivery), all under .product/. Every product has one home,
.product/products/<name>/; the reference What lives in
.product/products/product-cli/.
Graph-only. This repo was pivoted to the framework graph alone. The former FT/ADR/TC knowledge-graph tool (the
adr/test/gap/drift/conformance/implement/verifycommands,docs/{features,adrs,tests}, and the meta-graph engine) has been removed. Don't reach for those commands or dirs. Note the currentproduct featurecommand is unrelated — it is the §7.1 delivery feature (see Vocabulary below), not the old FT-XXX artifact.
Build & Test
cargo build # compile
cargo t # full suite, runs every binary (alias in .cargo/config.toml)
cargo clippy -- -D warnings -D clippy::unwrap_used # lint (zero unwrap policy)
Always run cargo t, never plain cargo test. Plain cargo test stops at
the first failing binary and skips the rest. The t alias is test --no-fail-fast (.cargo/config.toml): it runs every test binary and reports
the complete result set at the end.
Suite composition (~500 tests):
| Binary | What it covers |
|---|---|
cargo test -p product-core --lib |
pf unit tests (the framework graph, in #[cfg(test)] mod tests) |
cargo test -p product-mcp |
MCP registry + framework tool handlers (stateless + phase-gated session) |
--test framework |
assert_cmd-driven framework CLI scenarios (tests/framework.rs) |
--test code_quality_tests |
fitness gates: file length ≤ 400, function length, SRP, module structure |
product-core/tests/property |
proptest over fileops/init |
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 · 523 lines · 8,401 tokens per session scan A 2d23f357c6de
product-cli CLAUDE.md is an instructions file published in the GitHub repository Hafeok/product-cli (6 stars, last pushed 5d ago), licensed MIT. It adds 8,401 tokens to every session, about $0.0420 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.