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 skills/cmdr-chara/codex-toolkit/repository-intelligencenpx skills add cmdr-chara/codex-toolkit --skill repository-intelligencegit clone --depth 1 https://github.com/cmdr-chara/codex-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cmdr-chara/codex-toolkit/repository-intelligence)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/repository-intelligence"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/repository-intelligence.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00080 | $0.01847 |
| Opus 5 | $0.00040 | $0.00924 |
| Sonnet 5 | $0.00016 | $0.00369 |
| Haiku 4.5 | $0.00008 | $0.00185 |
Grade A, and why
repository-intelligence 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Intelligence
Produce a decision-grade map before high-blast-radius work. Analyze; do not silently edit.
Trigger boundary
Use this skill for requests such as:
- “Map the architecture and service boundaries before we change authentication.”
- “What consumes this schema, and what is the blast radius?”
- “Find ownership gaps, risky hubs, and likely merge-conflict surfaces.”
- “Explain where a new capability belongs without modifying the repository.”
Do not trigger for:
- assigning tasks or spawning agents—use
multi-agent-work-coordinatorafter the map exists; - explaining one observed failure—use
debugging-investigator; - executing a planned upgrade—use
codebase-evolution-controller; - a narrow symbol lookup that does not need architecture or impact reasoning.
Required inputs
Obtain or state:
- repository root and current working-tree state;
- decision to inform or proposed change hypothesis;
- base/head refs when impact is diff-driven;
- depth and excluded areas, including generated or vendored code;
- evidence constraints, such as unavailable history or missing build tooling.
If the change is unspecified, map the repository generally but label change-impact conclusions as provisional.
Safety baseline
- Inspect
git status --shortbefore analysis. Never assume a clean tree. - Do not checkout, reset, clean, stash, reformat, regenerate, or install dependencies.
- Treat uncommitted files as user work and include them in conflict analysis when relevant.
- Keep generated, vendored, cache, and dependency directories out of source statistics unless they are the subject.
- Never infer ownership solely from directory names or a single
git blameline.
Workflow
1. Frame the decision
Write a one-sentence intelligence question and an evidence threshold. Examples:
Question: Which components, contracts, and operational surfaces can be affected by changing session token rotation?
Threshold: Every high-confidence edge must cite a manifest, import, call site, schema, CI/deploy file, owner rule, or history sample.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 193 lines · 80 tokens per session scan A a648c82a6c30
repository-intelligence is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 6d ago), licensed MIT. It adds 80 tokens to every session and 1,847 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
boss-advanced
Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
briefing-vault
Initialize, manage, and search the per-project .briefing/ vault. Obsidian-compatible persistent knowledge base.
manage-skills
세션 변경사항을 분석하여 검증 스킬 누락을 탐지합니다. 기존 스킬을 동적으로 탐색하고, 새 스킬을 생성하거나 기존 스킬을 업데이트한 뒤 CLAUDE.md를 관리합니다.
release
Bump package.json version and create a git tag for npm release. Accepts semver bump type (patch/minor/major) or explicit version.