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.
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/commands/kumaran-is/claude-code-onboarding/audit-skills)<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/audit-skills"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/audit-skills.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 5.1 | $0.00088 | $0.01920 |
| Opus 5 | $0.00044 | $0.00960 |
| Sonnet 5 | $0.00018 | $0.00384 |
| Haiku 4.5 | $0.00009 | $0.00192 |
Grade A, and why
audit-skills 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 4d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit all skills in .claude/skills/ and agents in .claude/agents/. Score each against the 16-criterion rubric below. Output a graded report with prioritised fixes.
Scoring Rubric (16 criteria × 2 points = 32 points max)
Each criterion scores 0 (fail), 1 (partial), or 2 (pass).
Category A — Iron Law & Trigger (8 pts)
| # | Criterion | 2 (pass) | 1 (partial) | 0 (fail) |
|---|---|---|---|---|
| A1 | Iron Law present | ## Iron Law, **Iron Law:**, or > **Iron Law:** found in body |
Mandatory action present but not labelled Iron Law | Absent |
| A2 | Description has CSO trigger words | Contains specific trigger verbs: "Use when", "Triggers when", "Invoke for" + concrete scenario | Has trigger words but vague ("use for general...") | Missing or < 10 words |
| A3 | Trigger is unambiguous | Would NOT fire on tasks outside its domain | Could plausibly fire on 2+ unrelated task types | Fires on everything / too broad |
| A4 | No overlap with peer skills | No functional duplication with another skill in .claude/skills/ |
Minor overlap, clearly differentiated | Significant duplication — consolidate |
Category B — Structure & Size (8 pts)
| # | Criterion | 2 (pass) | 1 (partial) | 0 (fail) |
|---|---|---|---|---|
| B1 | Frontmatter complete | name, description, allowed-tools all present |
2 of 3 present | Missing or malformed frontmatter |
| B2 | Body ≤ 500 lines | ≤ 450 lines | 451–500 lines | > 500 lines |
| B3 | Progressive disclosure | Content ordered: summary → key rules → examples → reference | Mostly ordered, minor issues | Dumps everything upfront with no structure |
| B4 | References section | references/ dir present OR inline links to MCP/docs |
Referenced in body but dir missing | No references anywhere |
Category C — Content Quality (8 pts)
| # | Criterion | 2 (pass) | 1 (partial) | 0 (fail) |
|---|---|---|---|---|
| C1 | MCP server named explicitly | Specific MCP server listed (e.g. dart-mcp-server, context7, angular-cli) |
Generic "use MCP" without naming which | No MCP reference for a tech that has one |
| C2 | Code examples present | ≥ 1 concrete code block showing correct usage | Examples described in prose only | No examples |
| C3 | Anti-patterns documented | ≥ 1 explicit "don't do this" section or callout | Anti-patterns implied but not explicit | Absent |
| C4 | Stack version pinned | Specific version referenced (e.g. "NestJS 11.x", "Flutter 3.41.x") | Stack named without version | No stack version |
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.
- 4d ago First seen · 144 lines · 0 tokens per session scan A 616f930521e9
audit-skills is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 1,920 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.