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 tomzx/agents --skill find-code-duplicationgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/find-code-duplication)<a href="https://agentmods.dev/skills/tomzx/agents/find-code-duplication"><img src="https://agentmods.dev/badge/skills/tomzx/agents/find-code-duplication.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 | $0.00034 | $0.01955 |
| Opus 5 | $0.00017 | $0.00978 |
| Sonnet 5 | $0.00007 | $0.00391 |
| Haiku 4.5 | $0.00003 | $0.00196 |
Grade A, and why
find-code-duplication 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TODAY=!date +%Y-%m-%d
Find Code Duplication
Detects copy-pasted blocks and near-duplicate logic across the codebase and produces a prioritized extraction plan. Duplicated code multiplies the cost of every future change and is a leading source of bugs where a fix is applied in one copy but not others.
Prerequisites
- Working directory is the root of the repository
- Optional:
$1— path to limit the scan (defaults to.) - Language-specific tools (degrades to heuristics if unavailable):
- Any language:
jscpd(npm install -g jscpd) - Python:
pylintsimilarity checker orflake8-bugbear - Java/others:
cpd(from PMD,brew install pmd)
- Any language:
What to Look For
| Type | Description | Threshold to flag |
|---|---|---|
| Exact duplication | Identical code blocks copy-pasted verbatim | ≥ 5 lines |
| Near-duplication | Same structure with minor variations (different variable names, literals) | ≥ 8 lines |
| Structural duplication | Same algorithm implemented independently in multiple places | Judgment |
| Cross-file patterns | The same sequence of operations repeated across many call sites | ≥ 3 occurrences |
Steps
1. Detect Language and Available Tools
find ${1:-.} -type f | sed 's/.*\.//' | sort | uniq -c | sort -rn | head -10
command -v jscpd && jscpd --version
command -v cpd && cpd --version 2>/dev/null
2. Run Duplication Detector
jscpd (preferred — language-agnostic, handles near-duplicates):
jscpd ${1:-.} \
--min-lines 5 \
--min-tokens 50 \
--reporters console,json \
--output .jscpd-report \
--ignore "**/*.test.*,**/*.spec.*,**/node_modules/**,**/.venv/**" \
2>/dev/null | tail -60
Parse the JSON report for the top duplicates:
python3 -c "
import json, sys
try:
data = json.load(open('.jscpd-report/jscpd-report.json'))
dupes = data.get('duplicates', [])
dupes.sort(key=lambda d: d.get('lines', 0), reverse=True)
for d in dupes[:20]:
a = d['firstFile']
b = d['secondFile']
print(f\"{d.get('lines',0):4d} lines {a['name']}:{a['start']} <-> {b['name']}:{b['start']}\")
except: pass
" 2>/dev/null
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 · 211 lines · 34 tokens per session scan A f1c9d12c9bbc
find-code-duplication is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 1,955 once invoked, about $0.0002 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.
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…