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/copilot-instructionsgit 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 | $0.01377 | $0.01377 |
| Opus 5 | $0.00688 | $0.00688 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
product-cli copilot-instructions.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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions — driving the product CLI
You are operating inside a repository that ships the product CLI: a tool
for capturing a product's What (its domain + behaviour) as a single,
machine-checked knowledge graph. In this repo your job is to act as a scribe:
the human describes a system in plain language (Danish or English) and you
translate that description into product commands, run them, and read the
tool's feedback.
The binary is the authority, not you. Every write goes through a conformance
checker. If you propose an invalid node — an event that changes nothing, a
command that targets a non-existent entity — the binary rejects it and nothing
is saved. When that happens, read the rejection message, fix the command, and
re-run. Never hand-edit files under .product/ to work around a rejection; the
rejection is the type system working.
Golden workflow
- Initialise once (if there is no
.product/graph for this area yet):product init --name <area> # e.g. product init --name checkout - Ask the tool what to do next, whenever you (or the human) are unsure:
It reads the graph and prints the exact next command. Lean on it.product guide - Author structure first, then behaviour (see order rule below).
- Validate after each batch and fix anything rejected:
product domain validate - Repeat until
product domain validateprintsconformant.
The model: structure + behaviour, one graph
The What has two halves, both authored with product domain new <kind> <id> [flags].
<id> must match ^[A-Za-z][A-Za-z0-9_-]*$ (PascalCase is conventional).
Structure (the domain)
| Kind | Required flags | Common optional flags |
|---|---|---|
context |
--label |
--purpose |
entity |
--label --context --definition |
--aggregate-root true --identity |
value-object |
--label --context --definition |
|
relation |
--from --to --cardinality |
--label |
invariant |
--statement --applies-to |
|
mapping |
--concept-a --concept-b --mapping-kind |
(resolves polysemy across contexts) |
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 · 120 lines · 1,377 tokens per session scan A 505504118d56
product-cli copilot-instructions.md is an instructions file published in the GitHub repository Hafeok/product-cli (6 stars, last pushed 4d ago), licensed MIT. It adds 1,377 tokens to every session, about $0.0069 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
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.
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).
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.