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/preflightgit 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 | $0.00019 | $0.00482 |
| Opus 5 | $0.00010 | $0.00241 |
| Sonnet 5 | $0.00004 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
preflight scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Wait for healthy: `curl -sf http://localhost:7475 > /dev/null` What it actually says
Pre-flight Check (Step 0)
Run all checks before starting any implementation work. Report pass/fail for each.
Checks
1. Git state
git branch --show-current
git status -s
git log --oneline -3
- Must be on a feature branch (feat/, fix/, chore/) — NOT on main, release, hotfix, or dev
- Working tree should be clean (untracked
.claude/files are OK)
2. Neo4j container
docker ps --format '{{.Names}} {{.Status}}' | grep codegraph-neo4j
- If not running:
cd codegraph && docker compose up -d - Wait for healthy:
curl -sf http://localhost:7475 > /dev/null
3. Python venv
.venv/bin/codegraph --help > /dev/null 2>&1
- If missing:
python3 -m venv .venv && .venv/bin/pip install -e ".[python,mcp,test]"
4. Test suite
.venv/bin/python -m pytest tests/ -q
- All tests must pass before starting new work
5. Graph state
.venv/bin/codegraph query "MATCH (n) RETURN count(n) AS nodes"
- If 0 nodes: suggest running
/graph-refresh
Report
Pre-flight Report
-----------------
Git branch: feat/issue-N-slug ✅ / ❌ (on {protected branch})
Working tree: clean ✅ / dirty ❌
Neo4j: running ✅ / down ❌ (fixed ✅)
Python venv: OK ✅ / missing ❌ (fixed ✅)
Tests: {N} passed ✅ / {N} failed ❌
Graph: {N} nodes ✅ / empty ❌
Ready to work: YES / NO — fix {issues} first
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 · 60 lines · 19 tokens per session scan A f6f1a8244e02
preflight is a command published in the GitHub repository cognitx-leyton/codegraph (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 482 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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).