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/idoforgod/dissertation-simulator-agenticworkflow/installgit clone --depth 1 https://github.com/idoforgod/Dissertation-Simulator-AgenticWorkflowWhat 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 | $0.00620 |
| Opus 5 | $0.00005 | $0.00310 |
| Sonnet 5 | $0.00002 | $0.00124 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
install 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 Init 검증 결과 분석
.claude/hooks/setup.init.log 파일을 분석하고 문제를 해결합니다.
분석 프로토콜:
1단계 — 로그 읽기:
.claude/hooks/setup.init.log를 Read tool로 읽으세요.
파일이 없으면 사용자에게 안내: "claude --init으로 Setup Hook을 먼저 실행해야 합니다."
2단계 — 심각도별 분류:
- CRITICAL: Context Preservation System이 작동하지 않는 문제. 즉시 해결 필요.
- WARNING: 작동은 하지만 성능이 저하되는 문제. 해결을 권장.
- INFO: 정상 항목. 보고만.
3단계 — CRITICAL 문제 해결:
| 문제 | 해결 방법 |
|---|---|
| Script syntax error | 해당 스크립트를 Read → 구문 오류 위치 확인 → 수정 제안 |
| Script not found | 파일 누락 원인 조사. git status 확인 |
| context-snapshots/ 생성 실패 | 권한 문제 확인 (ls -la .claude/) |
| Python version < 3 | Python 3 설치 안내 |
| verification-logs/ 미존재 | 디렉터리 생성 제안 (워크플로우 실행 시 필요) |
| pacs-logs/ 미존재 | 디렉터리 생성 제안 (pACS 활성 워크플로우 시 필요) |
| autopilot-logs/ 미존재 | 디렉터리 생성 제안 (Autopilot 모드 시 필요) |
4단계 — WARNING 문제 해결:
| 문제 | 해결 방법 |
|---|---|
| PyYAML 미설치 | pip install pyyaml 실행 제안 (사용자 확인 후) |
| .gitignore 누락 | .gitignore에 .claude/context-snapshots/ 추가 제안 |
| sessions/ 생성 실패 | 상위 디렉터리 권한 확인 |
| SOT write safety 경고 | Hook 스크립트에서 SOT 파일명+쓰기 패턴 공존 감지. 해당 스크립트:줄번호 확인 → SOT 읽기 전용 원칙(절대 기준 2) 위반 여부 분석 |
5단계 — 최종 보고: 구조화된 형식으로 결과를 보고하세요:
## Setup Init 결과
### 검증 요약
- 전체: N개 항목
- 통과: N개
- 실패: N개 (CRITICAL: N, WARNING: N)
### 해결한 문제
- [문제 내용] → [해결 방법] → [결과]
### 남은 문제 및 권장 조치
- [문제 내용] → [권장 조치]
### Context Preservation System 상태
- [정상 / 성능 저하 / 작동 불가]
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 · 58 lines · 11 tokens per session scan A 5ba8cdc689c8
install is a command published in the GitHub repository idoforgod/Dissertation-Simulator-AgenticWorkflow (107 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 620 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.