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/rules-distill)<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/rules-distill"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/rules-distill.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 | $0.00000 | $0.00831 |
| Opus 5 | $0.00000 | $0.00415 |
| Sonnet 5 | $0.00000 | $0.00166 |
| Haiku 4.5 | $0.00000 | $0.00083 |
Grade A, and why
rules-distill 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rules-distill — Distill Skill Patterns Into Rules
Scan all skills for repeated behavioral patterns and promote high-value ones to rules.
Iron Law
Only promote patterns with evidence in 2+ skills AND a clear violation scenario — no speculative rules.
Usage
/rules-distill # Scan all skills
/rules-distill flutter # Scan only Flutter skills
/rules-distill security # Scan only security-related skills
What It Does
Runs the 3-phase pipeline:
- Inventory — Find all skills + rules files, build index of behavioral claims
- Cross-Read & Match — Find patterns appearing in 2+ skills, apply 4 filters
- User Review — Present candidates with verdict options, get approval before writing
4 Promotion Filters (all must pass)
| Filter | Test | Fail = Skip |
|---|---|---|
| 2+ skills evidence | Pattern found in ≥ 2 separate skill files | Appears in only 1 skill |
| Actionable behavior | Claude can detect violation at write time | Vague preference ("write clean code") |
| Violation risk | Missing this causes real bugs or inconsistency | Low-stakes style preference only |
| Not already in rules | Pattern NOT already in .claude/rules/*.md |
Already covered |
Verdict Taxonomy
| Verdict | Meaning | Action |
|---|---|---|
Append |
New rule fits cleanly in an existing rules file | Add to bottom of named file |
Revise |
Existing rule in rules file needs strengthening | Edit the specific rule |
New Section |
New rules file section needed | Add H2 section to named file |
New File |
Cross-cutting enough to warrant its own file | Create new .claude/rules/xxx.md |
Already Covered |
Pattern exists in rules — show exact file:line | Skip |
Too Specific |
Pattern belongs in a skill, not a rule | Skip — stays in skill |
Output Format (Phase 3 — User Review)
For each candidate, show:
## Candidate N: [Pattern Name]
**Evidence:**
- `skills/flutter-mobile/SKILL.md:47` — [quote]
- `skills/nestjs-api/SKILL.md:82` — [quote]
**Proposed Rule:**
> [One sentence rule, starting with "Always" or "Never" or a verb]
**Violation Scenario:**
> [One sentence: what breaks if this rule is absent]
**Verdict:** [Append to `rules/code-standards.md` / Revise / New Section / New File / Too Specific]
**Awaiting: APPROVE / SKIP / MODIFY**
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 · 93 lines · 0 tokens per session scan A 4770e2077e6c
rules-distill is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 831 tokens. 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.