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/kanyun-inc/reskill/code-confidence-mapnpx skills add kanyun-inc/reskill --skill code-confidence-mapgit clone --depth 1 https://github.com/kanyun-inc/reskillWhat 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 | $0.00104 | $0.03455 |
| Opus 5 | $0.00052 | $0.01728 |
| Sonnet 5 | $0.00021 | $0.00691 |
| Haiku 4.5 | $0.00010 | $0.00346 |
Grade A, and why
code-confidence-map 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.
How it starts
The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Confidence Map
Helps AI agents answer a core question: "If this code breaks tomorrow, how well-equipped are we to understand and fix it?"
This is NOT a linter or code quality tool. It measures comprehensibility risk — the gap between code complexity and human understanding. The AI's unique advantage over static analysis tools is semantic judgment: it can tell that processData does 5 unrelated things, that tests only cover happy paths, or that // don't touch this is a red flag.
When to Use This Skill
Use this skill when the user:
- Asks about code confidence, risk, or maintainability
- Says "is this code safe to change?" or "how risky is this module?"
- Is onboarding to a new codebase and wants to understand the landscape
- Wants to know where the tech debt or weak spots are
- Asks "which parts of the codebase are well-tested?"
- Says "scan this directory" or "check this file's health"
- Is planning a refactor and wants to assess risk first
- Asks about code quality, code health, or how solid a module is
Core Concept: What "Confidence" Means
Confidence is the answer to: "If something goes wrong here, can we understand and fix it?"
It is NOT:
- A judgment on code quality (LOW confidence is a risk signal, not a verdict)
- A measure of cleverness or elegance
- An indicator of who wrote the code or when
Confidence levels:
| Level | Meaning |
|---|---|
| HIGH | Well-tested, readable, good error handling — safe to work with |
| MEDIUM | Partially covered — some gaps in tests, docs, or error handling |
| LOW | Significant gaps — risky to modify without additional preparation |
Do NOT use percentages (e.g., "73.2%"). They imply false precision for what is fundamentally a judgment call.
Overall level rule: The overall confidence level equals the lowest dimension level. If any single dimension is LOW, the overall is LOW — one critical gap is enough to make code risky to work with.
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 · 349 lines · 104 tokens per session scan A 1532c90f5bce
code-confidence-map is a skill published in the GitHub repository kanyun-inc/reskill (59 stars, last pushed 22d ago), licensed MIT. It adds 104 tokens to every session and 3,455 once invoked, about $0.0005 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 skills, from other repositories
brooks-harness
Maintenance orchestrator for the brooks-lint plugin itself. Runs a sequential subagent pipeline — author → eval → QA → trigger-audit → release — to add or edit a skill, refresh the eval suite, keep the four manifests + all README translations + CHANGELOG + AGENTS/GEMINI in sync, audit trigger boundaries, and cut…
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
brooks-audit
Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codebase is organized…
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
brooks-debt
Tech debt assessment that identifies, classifies, and prioritizes maintainability problems — helping teams build a refactoring roadmap — drawing on twelve classic engineering books. Triggers when: user asks about tech debt, refactoring priorities, what to clean up first, or asks "why is this so hard to change?", "what…