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/humanity4ai/project_human/copilot-instructionsgit clone --depth 1 https://github.com/humanity4ai/project_humanWhat 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 | $0.00563 | $0.00563 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
project_human 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 3d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions
These instructions apply to all Copilot coding agent and Copilot code review activity in this repository.
Stack rules
- pnpm only (respect
packageManagerpin; commit lockfile changes) — never npm/yarn - TypeScript strict; no
any; ESM; Zod for runtime validation - Conventional commits; PR-only changes; never commit secrets or
.env - Do not weaken CI steps, tests, or coverage to force green — document pre-existing failures instead
MCP tools — use ALL available, for their strengths
| Tool | Use it for |
|---|---|
context7 (resolve-library-id, get-library-docs) |
Any library/framework API question — check docs before writing API code; never guess signatures |
perplexity (perplexity_search/ask/reason/research) |
Current best practices, comparisons, error diagnosis, multi-source research |
brave-search (brave_web_search, brave_news_search) |
Real-time facts, release notes, changelogs, breaking changes |
| Playwright (default) | Verify UI changes render correctly; check console errors; screenshot before finishing frontend work |
| GitHub (default) | Issues, PRs, code search, prior art in this and related repos |
If an MCP tool fails, report the error and continue with the remaining tools — never skip verification silently.
Custom agents in this repo
- software-developer — all code changes (features, fixes, refactors)
- researcher — R&D, technology evaluations, decision records (documents only, no code)
- writer-publisher — content, docs, i18n, translations in multiple languages/styles/tones/formats
Choose the agent matching the task type; combine researcher → software-developer for research-driven implementation.
Repo specifics
- pnpm monorepo:
@humanity4ai/mcp-servers(publishable,dist/committed) +@humanity4ai/evals - Rule-based MCP server — NO LLM calls in handlers; patterns live in
src/patterns.ts - Crisis resources only in
src/crisis-resources.ts— never hardcode phone numbers elsewhere - Coverage thresholds: mcp-servers 90% stmts/83% branches, evals 78/65 — new conditionals need tests
- Nine skills only (no grief-loss-support, no 10th skill); schemas in
schemas/ - Required checks:
validate (22)+CodeQL; ESM with.jsextensions in relative imports (NodeNext) - Pre-commit:
pnpm check && pnpm evals && pnpm test
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.
- 3d ago First seen · 41 lines · 563 tokens per session scan A 50bcb5296b21
project_human copilot-instructions.md is an instructions file published in the GitHub repository humanity4ai/project_human (4 stars, last pushed 5d ago), licensed MIT. It adds 563 tokens to every session, about $0.0028 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
Codex-Skills AGENTS.md
Instructions for TheGoat395/Codex-Skills, covering repository operating notes, required checks, evidence rules and change hygiene.
Ctxo CLAUDE.md
Instructions for alperhankendi/Ctxo, covering claude.md — ctxo, project overview, quick reference, dev (pnpm workspace) and usage (consumer).
apex-accelerator iac-bicep-best-practices.instructions.md
Bicep-specific IaC best practices for Azure templates. Security baseline, naming, AVM mandate, anti-patterns.
llm-ide-rules pytest-integration-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering pytest integration tests and example integration test.
humane-agentic-design CLAUDE.md
Instructions for glebis/humane-agentic-design, covering claude.md, what this repository is, rule ownership, what we deliberately do not cover and authoring conventions.
OpenGUI CLAUDE.md
Claude Code instructions for Core-Mate/OpenGUI, covering opengui release - repository guide for claude code / codex, 1. repository positioning, 2. default working rules, 3. high-level architecture and 4. directory map.