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/cognitx-leyton/codegraph/commitgit clone --depth 1 https://github.com/cognitx-leyton/codegraphWhat 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 | $0.00013 | $0.00425 |
| Opus 5 | $0.00006 | $0.00212 |
| Sonnet 5 | $0.00003 | $0.00085 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
commit 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
Commit (Step 6)
Create an atomic commit for the current changes.
Files to include: $ARGUMENTS (if empty, include all relevant modified/new files)
Process
1. Review what's being committed
git status -s
git diff --stat
git diff --cached --stat
Show the user a summary of changes before proceeding.
2. Stage files
git add <specific files>
Do NOT stage:
.claude/settings.local.json.claude/agents/(user-local).claude/skills/(user-local).env, credentials, secrets.superset/
3. Write commit message
Format:
<type>(<scope>): <concise description of WHY>
<Detailed body explaining what changed and the motivation.
Reference issue numbers if applicable.>
Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
Type: feat | fix | docs | refactor | test | chore
Scope: the module or area changed (e.g., parser, resolver, cli, mcp)
4. Commit
Use HEREDOC for proper formatting:
git commit -m "$(cat <<'EOF'
<type>(<scope>): <description>
<body>
Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
EOF
)"
5. Confirm
git log --oneline -1
git status -s
Report: commit SHA, message summary, remaining uncommitted files (if any).
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 · 75 lines · 13 tokens per session scan A dc06eae6bc87
commit is a command published in the GitHub repository cognitx-leyton/codegraph (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 425 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
feedback
Security Design Review — PRD/기획서 기반 보안 의견서·검토 의견서 생성.
compliance
이전 보안 진단 보고서의 Finding들이 패치되었는지 확인하고, 변경된 코드에서 신규 취약점을 탐색합니다.
va
Vulnerability Assessment — 8차원 아키텍처 진단 + Self-Verify + Evidence Verification.
pentest
Penetration Testing — 시나리오 기반 모의해킹 + POC + 라이브 검증 (State Delta 기반).
redteam
Red Team Operations — 인프라 설정 보안 리뷰 + MITRE ATT&CK + Detection Engineering.
verify
Adversarial Verification — 보안 진단 보고서 독립 검증 (Autonomous First).