project_human copilot-instructions.md

A repository-specific instruction guide for GitHub Copilot, an AI coding assistant. It defines the project’s coding rules, approved tools, and stack conventions.

In plain words
What is it for?
Guiding Copilot while it writes or reviews code in this repository, including when to consult library documentation, research current changes, inspect GitHub, or verify user interfaces.
Why use it?
It gives the coding assistant consistent guidance, such as using pnpm, strict TypeScript, runtime validation, conventional commits, and protected tests and secrets.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/humanity4ai/project_human/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/humanity4ai/project_human

Made for: GitHub Copilot.

Per session 563 This file is loaded in full into every session.
When invoked 563 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 50bcb5296b21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.github/copilot-instructions.md · 41 lines

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 packageManager pin; 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 .js extensions in relative imports (NodeNext)
  • Pre-commit: pnpm check && pnpm evals && pnpm test

Read the full file on GitHub · 41 lines

Changes

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.

  1. 3d ago First seen · 41 lines · 563 tokens per session scan A 50bcb5296b21

Subscribe to this mod's changes

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.