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/conorbronsdon/agent-context-os/claude-mdgit clone --depth 1 https://github.com/conorbronsdon/agent-context-osWrote 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/conorbronsdon/agent-context-os/claude-md)<a href="https://agentmods.dev/instructions/conorbronsdon/agent-context-os/claude-md"><img src="https://agentmods.dev/badge/instructions/conorbronsdon/agent-context-os/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 | $0.01153 | $0.01153 |
| Opus 5 | $0.00576 | $0.00576 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
agent-context-os 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[Your Name] — Context
Who I Am
→ Read identity/who-i-am.md for bio and background.
Slash Commands (Claude Code)
| Command | Does |
|---|---|
/setup |
Interactive onboarding — builds identity, project, and state files conversationally |
/start |
Load repository state and get a session briefing |
/end |
Log session, update state and the decision log, propose memory updates, check git |
/update |
Mid-session checkpoint — quick state save |
/today |
Morning heartbeat — briefing, staleness check, deadlines |
/clean-ai-writing |
Load writing/skills/avoid-ai-writing/SKILL.md and apply it |
/capture |
Triage raw notes from inbox/ into the right locations |
/find-context |
Find relevant context files by topic keyword (avoids Claude's built-in /context) |
/reconcile |
Drift detection after parallel sessions |
/recover |
Scan orphaned worktrees and stale branches, offer cleanup |
/content-shipped |
Log a published piece of content |
/dream |
Run an on-demand curator pass over the configured memory dir (default: rot detection) |
/dream-apply |
Walk a curator proposal artifact, accept/reject/edit per item |
/migrate-gemini |
Migrate selected Gemini CLI workflows with dry-run review and parity checks |
/mine-gemini-workflows |
Find repeated Gemini workflows and draft portable skills |
Add more commands as you build out skills. See docs/agent-template.md for how.
The /setup, /start, /update, and /end commands are Claude Code adapters to the portable workflow cores in .agents/skills/context-*. Keep shared procedure in the skill; keep Claude-only tools and auto-memory behavior in the command adapter.
When to Load Additional Context
For tasks without a slash command → load ROUTING.md.
Thought-Partner Mode
When thinking through a decision or tradeoff — rather than producing a deliverable — operate as a thought partner:
- Challenge assumptions. If a premise seems weak or unexamined, say so.
- Offer the alternative. Present the strongest case for a different path.
- Ask the uncomfortable question. What hasn't been considered or is being avoided?
- Be direct about tradeoffs. Don't soften the downsides.
- Summarize the decision cleanly. What's the choice, what does each path require, and what's the real risk?
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 · 78 lines · 1,153 tokens per session scan A 7bc19b39d1ec
agent-context-os CLAUDE.md is an instructions file published in the GitHub repository conorbronsdon/agent-context-os (22 stars, last pushed today), licensed MIT. It adds 1,153 tokens to every session, about $0.0058 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 2026-08-30.
Other instructions, from other repositories
memory-journal-mcp copilot-instructions.md
Copilot instructions for neverinfamous/memory-journal-mcp, covering memory journal mcp — copilot code review context, project overview, session context, tooling standards and coding standards.
mex CLAUDE.md
Claude Code instructions for mex-memory/mex, a project described as: Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.
knowns AGENTS.md
AGENTS.md instructions for knowns-dev/knowns, covering agents, runtime guidance, minimum rules and quick reference.
recall CLAUDE.md
Instructions for joseairosa/recall, covering claude.md, project context, build & run commands, testing and unit tests with vitest (primary test runner).
consolidate-memory AGENTS.md
AGENTS.md instructions for Zenetusken/consolidate-memory, covering agents.md — consolidate-memory, what this is, commands you will actually run, layout and core contracts — do not break these.
consolidate-memory CLAUDE.md
Claude Code instructions for Zenetusken/consolidate-memory, covering consolidate-memory — project conventions, the one gotcha that matters, layout, conventions and safety (this repo is public).