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/graph-refreshgit 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 | $0.00018 | $0.00414 |
| Opus 5 | $0.00009 | $0.00207 |
| Sonnet 5 | $0.00004 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
graph-refresh 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
Why
codegraph is a static snapshot of the codebase at index time. Edits after indexing don't show up in the graph until you re-index. Run this command after any structural change — adding/removing classes, functions, methods, imports, decorators; renaming; moving files. For cosmetic edits (comment changes, reformatting), it's not necessary.
What this does
Re-parses every .py file under codegraph/codegraph/ and codegraph/tests/ and upserts nodes / edges into Neo4j. Does not wipe the rest of the graph — Twenty (or any other indexed TS repos) stays untouched. Typical runtime: ~5 seconds for both packages.
codegraph index \
/home/edouard-gouilliard/Obsidian/SecondBrain/Personal/projects/graphrag-code \
-p codegraph/codegraph \
-p codegraph/tests \
--no-wipe \
--skip-ownership
--no-wipe keeps other graphs alive. --skip-ownership skips the git-log pass (faster; owners can be added back later if needed).
After running
Re-run any /graph queries you had open — results should reflect the latest code. If something unexpected disappeared, it's more likely a parser edge case than a data loss: check the AST of the file in question, or open an issue.
Indexing a different repo
To point the graph at some other TS / Python repo:
codegraph index /path/to/repo -p <package>
Drop --no-wipe if you want to start from a clean graph (wipes everything, including the codegraph + Twenty snapshots).
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 · 38 lines · 18 tokens per session scan A c67620d1aa4b
graph-refresh is a command published in the GitHub repository cognitx-leyton/codegraph (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 414 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).