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/file-issuesgit 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 | $0.00011 | $0.00406 |
| Opus 5 | $0.00005 | $0.00203 |
| Sonnet 5 | $0.00002 | $0.00081 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
file-issues scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
File Issues (Step 11)
During implementation, you may discover:
- Enhancement ideas that are out of scope for the current work
- Bugs in unrelated code
- Missing features that would be nice to have
- Technical debt worth tracking
Do NOT implement these. File them as GitHub issues so they're tracked for future work.
Process
1. Review discoveries
Look through:
- Deviations noted during
/implement - Suggestions from
/review-prthat were out of scope - Ideas surfaced during
/critique - Errors seen during
/testthat aren't blockers
2. For each discovery, create an issue
gh issue create --title "<type>: <concise title>" --body "$(cat <<'EOF'
## Context
Discovered during implementation of <current work>.
## Description
<What the issue is, with specifics>
## Suggested approach
<Brief idea of how to address it, if known>
## References
- Related file(s): `<path>`
- Related commit: `<sha>`
- Surfaced by: `/review-pr` | `/critique` | `/test`
EOF
)" --label "<enhancement|bug|tech-debt>"
3. Report
Issues Filed
-------------
- #N: <title> (enhancement)
- #N: <title> (bug)
- #N: <title> (tech-debt)
These are tracked for future work — not part of the current release.
Ready for: /create-pr
Labels
| Label | When to use |
|---|---|
enhancement |
New feature or capability |
bug |
Something broken in existing code |
tech-debt |
Refactoring, cleanup, performance |
documentation |
Missing or outdated docs |
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 · 73 lines · 11 tokens per session scan A d63aca1ed35f
file-issues is a command published in the GitHub repository cognitx-leyton/codegraph (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 406 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).