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 ckorhonen/hone-skills --skill duplication-huntgit clone --depth 1 https://github.com/ckorhonen/hone-skillsWrote 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/ckorhonen/hone-skills/duplication-hunt)<a href="https://agentmods.dev/skills/ckorhonen/hone-skills/duplication-hunt"><img src="https://agentmods.dev/badge/skills/ckorhonen/hone-skills/duplication-hunt/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/ckorhonen/hone-skills/duplication-hunt"><img src="https://agentmods.dev/badge/skills/ckorhonen/hone-skills/duplication-hunt.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 | $0.00057 | $0.01525 |
| Opus 5 | $0.00028 | $0.00763 |
| Sonnet 5 | $0.00011 | $0.00305 |
| Haiku 4.5 | $0.00006 | $0.00153 |
Grade A, and why
hone:duplication-hunt 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 10d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Duplication Hunt
What This Skill Does
Scans source code to find duplicated patterns that indicate extraction opportunities. Goes beyond simple copy-paste detection to find three types of duplication:
- Exact duplicates: Identical code blocks (3+ lines) appearing in two or more locations.
- Renamed duplicates: Structurally identical code where only variable names, string literals, or numeric constants differ.
- Structural duplicates: Code blocks that follow the same control flow pattern (same sequence of operations, branches, and loops) with different specifics — the "same shape, different nouns" pattern.
Ranks findings by occurrence count and block size to surface the highest-value extraction candidates first.
When To Use
- On a weekly schedule as a codebase hygiene check.
- After a large feature merges to catch introduced duplication.
- When onboarding to a codebase to understand where abstractions are missing.
- When the user asks to "find duplicated code" or "hunt for duplication".
Do Not Use
- For method length — use
hone:method-brevity-auditinstead. - For naming quality — use
hone:intent-clarity-auditinstead. - For test naming — use
hone:test-naming-auditinstead. - For design-level duplication (repeated architectural patterns across services). This skill operates at the code block level.
- To auto-extract or refactor duplicates. This skill reports findings only.
Inputs To Confirm
- Scope: Which directories or file patterns to scan (default: entire repo, excluding vendored/generated code).
- Minimum block size: Smallest code block to consider, in lines (default: 4 lines).
- Minimum occurrences: How many times a pattern must appear to be reported (default: 2 for exact, 3 for structural).
- Exclusions: Glob patterns for files or directories to skip.
- Top-N: Maximum findings to report (default: 15).
Instructions
- Identify scannable files. Walk the repository tree. Exclude vendored
directories (
node_modules,vendor,dist,build,.git,__pycache__), generated files, lock files, and user-specified exclusions. Include test files in the scan — test duplication is also worth finding.
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.
- 10d ago First seen · 162 lines · 57 tokens per session scan A e833f58403fb
hone:duplication-hunt is a skill published in the GitHub repository ckorhonen/hone-skills (0 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,525 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
review-pr
Multi-agent PR review with four modes (review, re-review, self-review, address-feedback) - spawns parallel subagents, saves diff to /tmp for context efficiency, supports file exclusion patterns.
Biome
Biome 2.x — fast all-in-one web toolchain in Rust. Formats, lints, assists. Replaces Prettier + ESLint.
biome
Biome - Fast all-in-one toolchain for web projects (linter + formatter in Rust, 100x faster than ESLint).
vibe-check
Audit code for "vibe coding sins" — patterns that indicate AI-generated code was accepted without proper review. Produces a scored report card with fix suggestions.
ruff-docs
Ruff — fast Python linter and formatter in Rust. 900+ rules, Black-compatible formatter, LSP, CI/CD.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.