project_human AGENTS.md

Project-specific instructions for humanity4ai/project_human, including its architecture, commands, coverage requirements, and development environment. A monorepo is one repository containing multiple packages.

In plain words
What is it for?
Use them when editing this repository, especially when running tests, builds, checks, evaluations, or commands for its two packages.
Why use it?
They prevent developers and agents from running checks in the wrong place or changing project files without keeping the architecture and documentation consistent.

Instructions file for CodexOpenCode

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/agents-md
Clone the repo
git clone --depth 1 https://github.com/humanity4ai/project_human

Made for: Codex, OpenCode.

Per session 2,549 This file is loaded in full into every session.
When invoked 2,549 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 $0.02549 $0.02549
Opus 5 $0.01274 $0.01274
Sonnet 5 $0.00510 $0.00510
Haiku 4.5 $0.00255 $0.00255

Measured 2d ago against content hash f3263f31ee46, 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 AGENTS.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.

AGENTS.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Agentic Coding Guidelines


CRITICAL: All compute in GitHub Codespaces

NEVER run compilation, testing, builds, linting, or installs on the local machine. These operations are blocked in opencode.json and must run in a GitHub Codespace.

gh cs ssh <name> -- "cd /workspaces/project_human && pnpm check"
gh cs cp <changed-file> remote:/workspaces/project_human/<path>

Sync files to your codespace after making edits, then run verification there.


Commands (Codespace only)

pnpm monorepo. Two packages: @humanity4ai/mcp-servers (publishable) and @humanity4ai/evals (private).

pnpm check          # tsc --noEmit across all packages
pnpm start          # MCP server via tsx (stdio transport)
pnpm test           # vitest run (both packages)
pnpm test:coverage  # vitest --coverage
pnpm evals          # skill eval harness (10 checks: 9 skills + contract-consistency)
pnpm build          # compile mcp-servers → dist/

Single test / single package:

pnpm --filter @humanity4ai/mcp-servers test -- --test-name-pattern "H-1"
pnpm --filter @humanity4ai/mcp-servers test -- src/__tests__/handlers.test.ts
pnpm --filter @humanity4ai/mcp-servers check
pnpm --filter @humanity4ai/evals test

Pre-commit (run in codespace): pnpm check && pnpm evals && pnpm test. CI order: checkbuildEVAL_REPORT=1 pnpm evalstest:coverage (both packages).


Coverage Thresholds

Package Stmts Branch Funcs Lines
mcp-servers 90% 83% 90% 90%
evals 78% 65% 80% 78%

Excluded from coverage (vitest.config.ts): bin.ts, accessibility-engine.ts, server-factory.ts. wcag-criteria.ts included (96% covered by modules.test.ts). New conditionals → new tests in __tests__/modules.test.ts.


Architecture

Package layout

  • mcp-servers/src/server-factory.ts — shared createServer() → registers all 9 tools on an McpServer. Used by both stdio (mcp-server.ts) and HTTP (api/mcp.ts) transports.
  • mcp-servers/src/mcp-server.ts — thin stdio wrapper: imports factory, connects StdioServerTransport. Re-exports handlers + VERSION for test compatibility.
  • mcp-servers/api/mcp.ts — Vercel serverless function using StreamableHTTPServerTransport in stateless mode. Imports factory + handlers from npm package.
  • mcp-servers/src/schemas-data.ts — auto-generated at build time: all 18 JSON schemas as inline JS objects. validate.ts imports this instead of readFileSync — zero file I/O, works in all bundler environments (Vercel, Cloudflare).
  • mcp-servers/src/validate.ts — input validation against inline SCHEMA_REGISTRY. No node:fs dependency. Called by invokeAction at handler dispatch time.
  • mcp-servers/src/handlers.ts — 9 private handler functions + invokeAction(action, input) dispatcher.
  • knowledge-core/taxonomy.ts — canonical CATEGORY_SLUGS + ESCALATION_REQUIRED_SKILLS (typed const arrays). taxonomy.md is the human-readable reference.
  • evals/src/run-evals.ts — parses VALID_CATEGORIES from knowledge-core/taxonomy.md at runtime (no hardcoded duplicate). 10 checks: 9 skills + contract-consistency.

Read the full file on GitHub · 174 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. 2d ago First seen · 174 lines · 2,549 tokens per session scan A f3263f31ee46

Subscribe to this mod's changes

project_human AGENTS.md is an instructions file published in the GitHub repository humanity4ai/project_human (4 stars, last pushed 4d ago), licensed MIT. It adds 2,549 tokens to every session, about $0.0127 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.