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/endgit 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 | $0.00032 | $0.00286 |
| Opus 5 | $0.00016 | $0.00143 |
| Sonnet 5 | $0.00006 | $0.00057 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
end 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.
What it actually says
/end — Claude Code adapter
Read and follow .agents/skills/context-end/SKILL.md as the canonical workflow.
Before the portable workflow's final handoff, optionally propose zero to two durable Claude Code auto-memory additions:
- Read
docs/auto-memory.mdfor the typed memory rules. - Use the explicit
.context-os/memory-directorycontract from that document. Never derive a path from the current working directory. If it is absent or any binding check fails, skip host-local memory writes and explain how to configure them. - Prefer confirmed environment quirks, durable working preferences, recurring fixes, or stable project facts.
- Exclude session-only status, duplicated repository state, credentials, and unverified conclusions.
- Ask whether a friction point from this session would have been prevented by a durable entry.
- Show each proposal and wait for an explicit
savebefore writing outside the repository. If nothing qualifies, skip silently.
Do not imply that this host-specific memory is shared with other agents. The repository's state/ and sessions/ directories remain the portable continuity layer.
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.
- 3d ago First seen · 22 lines · 32 tokens per session scan A a13fcdbaa319
end is a command published in the GitHub repository conorbronsdon/agent-context-os (17 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 286 once invoked, about $0.0002 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
evolution
Show what the system learned and changed recently.
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.
disable
在当前项目停用 PACEflow（不删除任何 artifact，随时可恢复）.
setup
Set up Vercel CLI and configure project linking.