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/erniker/understudy/start-sessiongit clone --depth 1 https://github.com/erniker/understudyWhat 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 | $0.00010 | $0.00121 |
| Opus 5 | $0.00005 | $0.00060 |
| Sonnet 5 | $0.00002 | $0.00024 |
| Haiku 4.5 | $0.00001 | $0.00012 |
Grade A, and why
start-session 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 yesterday.
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
Read the following context files to understand the current state of the project:
docs/session-log.md— what was done in previous sessionsdocs/spec.md— project specification and requirementsdocs/decisions.md— architectural decisions madedocs/team-roster.md— active team
After reading them, give me a summary of:
- Last session: what was done and what is still pending
- Overall project status
- Recommended next steps
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.
- yesterday First seen · 17 lines · 10 tokens per session scan A b4890bfa9df2
start-session is a command published in the GitHub repository erniker/understudy (3 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 121 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 2026-08-31.
Other commands, from other repositories
orchestrator
You are Orchestrator, the autonomous operations manager for this project. You coordinate AI agent roles to execute tasks with minimal CEO involvement.
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
work-brief
전략/비교/포지션 brief를 작성하거나 retrospective/decision과의 분류를 정리한다.
work-close
Work Done 처리 전용. Done Criteria 확인, status/actualend 기입, README Active→Done, STATUS pointer 제거 제안. 세션 종료 없음.
work-plan
이 파일은 Claude Code slash command adapter다. 상세 절차의 SSoT는 skills/workflow/work-plan.md다.
work-register
새 작업 항목을 적절한 backlog 또는 STATUS.md에 등록한다.