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 skills add jonZlotnik/how-to-agent --skill dry-auditgit clone --depth 1 https://github.com/jonZlotnik/how-to-agentWrote 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/jonzlotnik/how-to-agent/dry-audit)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/dry-audit"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/dry-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/dry-audit"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/dry-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00054 | $0.00589 |
| Opus 5 | $0.00027 | $0.00295 |
| Sonnet 5 | $0.00011 | $0.00118 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
dry-audit 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 11d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DRY Audit
DRY is about knowledge, not characters. Two functions that look alike but encode different rules aren't duplication. One business rule encoded in code + config + docs + a test fixture is. The audit hunts for knowledge with more than one home.
When to use
- A change forces edits in 3+ files that "always have to move together"
- You're about to copy a block "just to tweak it slightly"
- Constants, enums, or strings appear in both code and configuration
- A schema lives in code and is re-described in markdown and a test fixture
Protocol
- Pick a piece of knowledge — a rule, threshold, name, schema, format. Not a function — a fact.
- Find every place it lives. Grep widely: code, tests, configs, env vars, fixtures, docs, comments, migrations.
- Mark one as canonical. Usually the one closest to the runtime decision (code beats doc, generator beats copy).
- Derive the rest. Generate, import, reference, or delete. The non-canonical copies should disappear or become provably-equal references.
- Defend the boundary. Add a test, type, or build step that fails if drift returns.
Worked example
A maxRetries=5 constant appears in client.ts, in config.yaml, in a README example, and as the literal 5 in a test. Real duplication. Canonical home: config.yaml. Code reads from config. README example links to the same key. Test reads it from the loaded config. One fact, one home, four references.
Red flags (rationalizations to reject)
- "These two functions just happen to look alike." — Then they'll drift. Either they encode the same rule (deduplicate) or different rules (rename to make the difference obvious).
- "It's only two places." — It's two places that will diverge silently the first time one is updated.
- "Documentation is supposed to repeat the code." — No: documentation should describe code, not encode the same facts in a form that can rot.
Composes with
- [[orthogonality-check]] — duplicated knowledge is one of the strongest coupling signals; the audits often surface the same modules.
- [[broken-windows]] — fresh duplication noticed early is a window. Patch it before it becomes the norm.
- [[design-by-contract]] — when a duplicated rule becomes a contract, the contract enforces the single source of truth.
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.
- 11d ago First seen · 40 lines · 54 tokens per session scan A bc06381d0e12
dry-audit is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 589 once invoked, about $0.0003 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…