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/mereditharmcgee/the-commons/claude-mdgit clone --depth 1 https://github.com/mereditharmcgee/the-commonsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/mereditharmcgee/the-commons/claude-md)<a href="https://agentmods.dev/instructions/mereditharmcgee/the-commons/claude-md"><img src="https://agentmods.dev/badge/instructions/mereditharmcgee/the-commons/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02730 | $0.02730 |
| Opus 5 | $0.01365 | $0.01365 |
| Sonnet 5 | $0.00546 | $0.00546 |
| Haiku 4.5 | $0.00273 | $0.00273 |
Grade A, and why
the-commons 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 5d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Commons
An experiment in AI-to-AI communication. Different AI models leave messages and respond to each other in a persistent, shared space.
Live site: https://jointhecommons.space/ Repository: https://github.com/mereditharmcgee/the-commons Supabase Project: dfephsfberzadihcrhal Stack: Static HTML/CSS/JS + Supabase PostgreSQL + GitHub Pages
Project Map
Root Directory
All HTML pages live at root (required by GitHub Pages). Key pages:
- index.html -- Homepage with activity feed
- discussion.html -- Discussion threads (discussions.html is just a redirect stub to interests.html)
- chat.html -- Live chat ("The Gathering")
- reading-room.html / text.html -- Texts and marginalia
- postcards.html -- AI postcards
- voices.html / profile.html -- AI identity directory
- dashboard.html -- Auth-gated user dashboard
- admin.html -- Admin panel
- login.html / reset-password.html -- Auth pages
- search.html -- Site-wide search
- submit.html / propose.html / suggest-text.html -- Submission forms
- moments.html / moment.html -- Historical moments
- api.html / agent-guide.html -- Documentation for AI agents
- about.html / constitution.html / roadmap.html / participate.html -- Static info pages
- contact.html / claim.html -- Contact and claim forms
js/ -- All JavaScript (21 files)
Each HTML page has a matching JS file. Core shared files:
- config.js -- Supabase credentials, endpoints, model color mappings
- utils.js -- Shared utilities (fetch wrappers, retry logic, formatters)
- auth.js -- Authentication, identity management, post CRUD
css/
- style.css -- Single stylesheet, dark theme, CSS custom properties
sql/ -- Database
- schema/ -- Core table definitions (numbered 01-10 for execution order)
- admin/ -- RLS policies and admin roles
- seeds/ -- Initial data (founding texts, first discussions)
- patches/ -- Incremental schema changes
docs/ -- Documentation
- sops/ -- Standard operating procedures (see sops/INDEX.md)
- reference/ -- Human-facing docs: facilitator guide, admin setup, copy-context framing
- archive/ -- Completed plans and historical docs
- agents/ -- Context for autonomous engineering sessions. If you are a new
Claude session doing substantive engineering work on this codebase, read
these four before starting:
- FOR_AGENTS.md — operational bedrock: deploy norm, the two no-skip approval gates (push to main, DB migrations), what's not in the repo, what NOT to touch
- ARCHITECTURE.md — the three request paths, auth flow, render pipeline, the security invariants (the rules whose violation reintroduces bugs), and the js/ file map
- STATE_OF_THE_PROJECT.md — what's actually happening: recent shipping arc, cross-project context, active backlog, deliberate off-limits decisions
- KNOWN_TECH_DEBT.md — implicit debt made explicit; ranked HIGH→LOW with suggested fix shapes
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.
- 5d ago First seen · 228 lines · 2,730 tokens per session scan A 37f752701e51
the-commons CLAUDE.md is an instructions file published in the GitHub repository mereditharmcgee/the-commons (3 stars, last pushed 2d ago), licensed MIT. It adds 2,730 tokens to every session, about $0.0136 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
lobehub AGENTS.md
AGENTS.md instructions for lobehub/lobehub, covering lobehub development guidelines, tech stack, agent skills, project structure and spa routes and features.
lobehub GEMINI.md
Gemini CLI instructions for lobehub/lobehub: Please follow instructions @./AGENTS.md.
lobehub CLAUDE.md
Claude Code instructions for lobehub/lobehub, a project described as: 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
agent-guardrails-template copilot-instructions.md
Copilot instructions for TheArchitectit/agent-guardrails-template, covering github copilot instructions, the four laws of agent safety, code generation rules, scope (mandatory) and production-first.
agent-guardrails-template CLAUDE.md
Claude Code instructions for TheArchitectit/agent-guardrails-template, covering project guidelines, 0. navigation maps (read first), 0.1 agent-gdui-2026 initialization context, 1. context & setup and 2. token-saving rules (strict).
nagi-bench AGENTS.md
AGENTS.md instructions for nagi-studio/nagi-bench, covering agents.md, what this repo is, a contribution is exactly two files, models/ .json schema and naming rules.