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 commands/conorbronsdon/agent-context-os/setupgit clone --depth 1 https://github.com/conorbronsdon/agent-context-osWhat 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 | $0.00011 | $0.00287 |
| Opus 5 | $0.00005 | $0.00143 |
| Sonnet 5 | $0.00002 | $0.00057 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
setup 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.
What it actually says
/setup — Claude Code adapter
Before delegating, disclose that Claude Code auto-memory is enabled by default
and may write machine-local memory automatically during ordinary sessions. The
user can inspect it with /memory or disable it with
autoMemoryEnabled: false in .claude/settings.local.json. This repository's
review gates govern its own lifecycle and /dream flows; they do not turn
ordinary host auto-memory into a reviewed write path. Do not change the setting
as part of setup.
Read and follow .agents/skills/context-setup/SKILL.md as the canonical workflow.
After the user approves the portable workflow's proposed changes:
- replace the
[Your Name]placeholder inCLAUDE.mdwhen a name was supplied and the placeholder still exists; - if the user wants a Claude Code slash command for a newly approved portable skill, create only a thin adapter in
.claude/commands/and add its row to the table inCLAUDE.md; and - offer, but never assume, a commit after showing the final diff and validation result.
Finish by mapping the portable lifecycle back to Claude Code: /start begins a session and /end closes it.
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.
- 2d ago First seen · 27 lines · 11 tokens per session scan A c1f64271e06d
setup is a command published in the GitHub repository conorbronsdon/agent-context-os (17 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 287 once invoked, about $0.0001 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 commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
whats-next
Show current project status and suggest next steps.
save
Save this conversation as a new or existing reusable context.
import
Import a shared context bundle, or take a teammate's newer copy of one you already have.
resume
恢复本 session 的 PACEflow（删除 pause 标志）.
extensions
Show what the connected context expects to reach, and whether this machine provides it.