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/roadmapgit 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 | $0.00010 | $0.00391 |
| Opus 5 | $0.00005 | $0.00196 |
| Sonnet 5 | $0.00002 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
roadmap 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
Update Roadmap (Step 8)
Update ROADMAP.md at the repo root to reflect what was just implemented.
Process
1. Gather context
git log --oneline $(git describe --tags --abbrev=0 2>/dev/null || echo HEAD~10)..HEAD
git diff --stat $(git describe --tags --abbrev=0 2>/dev/null || echo HEAD~10)..HEAD
Read the current ROADMAP.md.
2. Update these sections
"TL;DR — where we are"
- Update branch state, test count, graph stats, package version
"Shipped since the last roadmap update"
- Add new commit list with descriptions
- Group by theme (like existing entries)
"Repository state"
- Update table: branch, unpushed commits, test count, last install
"What's next (ranked)"
- Move completed items out of "What's next"
- Re-rank remaining items if priorities shifted
- Add any new items discovered during implementation
"Known open questions"
- Remove resolved questions
- Add new questions surfaced during work
3. Update the header
> **Last updated:** {today's date} after commits `{first}` → `{last}` ({summary}).
4. Do NOT update these sections
- "Session workflow conventions" — only update if a convention changed
- "Non-goals" — only update if something moved in/out of scope
- "Appendix" — auto-derived from code, update only if file structure changed
Validate
Read the updated ROADMAP.md back and verify it's coherent — a fresh agent should be able to pick up work from it.
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 · 56 lines · 10 tokens per session scan A 62dc50d2a4d6
roadmap is a command published in the GitHub repository cognitx-leyton/codegraph (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 391 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).