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/startgit 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 | $0.00027 | $0.00247 |
| Opus 5 | $0.00014 | $0.00123 |
| Sonnet 5 | $0.00005 | $0.00049 |
| Haiku 4.5 | $0.00003 | $0.00025 |
Grade A, and why
start 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
/start — Claude Code adapter
Read and follow .agents/skills/context-start/SKILL.md as the canonical workflow.
While performing its optional live-source step, use the gws CLI only when it is already installed and authenticated. Every CLI invocation requires the normal tool approval flow so the user can review the exact command and arguments:
- Calendar: list the primary calendar from today through the next seven days with single events ordered by start time; request only summary, start, end, and attendees.
- Gmail: optionally request the unread count only, with
is:unreadand a single-result limit. - Project trackers: read
state/gws-references.mdand query only identifiers the user placed there.
If the CLI or identifiers are unavailable, continue from repository state without treating that as an error. Do not authenticate, change configuration, use --page-all or --output, send messages, or write to any connected service.
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 · 19 lines · 27 tokens per session scan A e9c35f9216cf
start is a command published in the GitHub repository conorbronsdon/agent-context-os (17 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 247 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
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.