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/packagegit 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 | $0.00012 | $0.00438 |
| Opus 5 | $0.00006 | $0.00219 |
| Sonnet 5 | $0.00002 | $0.00088 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade C, and why
package scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s https://pypi.org/pypi/cognitx-codegraph/json | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(python:*), Bash(.venv/bin/*), Bash(grep:*), Bash(curl:*) What it actually says
Package (Step 9)
Bump the patch version, build the wheel + sdist, and publish to PyPI.
Process
1. Read current version
grep '^version' pyproject.toml
2. Bump patch version
Increment the patch number: 0.1.X → 0.1.X+1
Edit pyproject.toml to update the version.
3. Build
cd codegraph
rm -f dist/*
.venv/bin/python -m build
ls dist/
Verify both .whl and .tar.gz are produced.
4. Upload to PyPI
.venv/bin/twine upload dist/*
Uses credentials from ~/.pypirc. If upload fails, check:
- Token is valid
- Version doesn't already exist on PyPI
5. Verify on PyPI
curl -s https://pypi.org/pypi/cognitx-codegraph/json | python3 -c "
import sys, json
d = json.load(sys.stdin)
v = d['info']['version']
print(f'Latest version on PyPI: {v}')
print(f'URL: https://pypi.org/project/cognitx-codegraph/{v}/')
"
6. Report
Package Published
-----------------
Version: 0.1.{N}
PyPI: https://pypi.org/project/cognitx-codegraph/0.1.{N}/
Wheel: cognitx_codegraph-0.1.{N}-py3-none-any.whl
Install: pip install cognitx-codegraph==0.1.{N}
pipx install "cognitx-codegraph[python,mcp]==0.1.{N}"
Ready for: /test
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 · 71 lines · 12 tokens per session scan C 92407861267d
package is a command published in the GitHub repository cognitx-leyton/codegraph (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 438 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, 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).