Borrowing it
Nothing to install: this file belongs to rajbos/ai-engineering-fluency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rajbos/ai-engineering-fluency/main/.claude/skills/deduplicate-code/SKILL.mdgit clone --depth 1 https://github.com/rajbos/ai-engineering-fluencyWrote 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/rajbos/ai-engineering-fluency/deduplicate-code)<a href="https://agentmods.dev/skills/rajbos/ai-engineering-fluency/deduplicate-code"><img src="https://agentmods.dev/badge/skills/rajbos/ai-engineering-fluency/deduplicate-code/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/rajbos/ai-engineering-fluency/deduplicate-code"><img src="https://agentmods.dev/badge/skills/rajbos/ai-engineering-fluency/deduplicate-code.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 | $0.00107 | $0.02287 |
| Opus 5.5 | $0.00043 | $0.00915 |
| Sonnet 5.5 | $0.00021 | $0.00457 |
| Haiku 4.5 | $0.00011 | $0.00229 |
Grade A, and why
deduplicate-code 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 yesterday.
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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deduplicate Code
The CI step summary runs check-code-duplication.js and reports copy-pasted
blocks across the six TypeScript source trees every PR (the CI duplication-check job also fails when the
count grows past scripts/code-duplication-baseline.json, so remediating lets you lower that baseline). A growing "Code
Duplication Analysis" section (or a review finding of "this is duplicated")
is the signal this skill remediates: it finds the duplicate groups, picks
one, extracts a single shared helper in their place, and verifies nothing
broke. Like refactor-large-function, it changes one group per pass so the
diff stays reviewable and a regression points at a single extraction.
What the detector does
scripts/check-code-duplication.js (run as pnpm run check:duplicates from
vscode-extension/) normalizes source lines (whitespace collapsed, comment-only
and blank lines dropped so re-indented or re-commented copies are still caught),
hashes sliding windows of a minimum length, groups identical windows, and
extends each group to its maximal shared block. It reports clone groups as
Markdown (for the step summary) or --json. It is report-only by default (CI gates it only through --baseline);
this skill does the remediation the report asks for.
A "duplicate group" is a normalized sequence of >= --min-lines lines that
occurs in two or more places (cross-file, or non-overlapping within one file).
Step 1 - List the duplicate groups
Get the current clone groups in machine-readable form so you can pick a target:
node scripts/check-code-duplication.js --json --min-lines 14
Or, scoped to one area if the full scan is large:
node scripts/check-code-duplication.js --json --min-lines 14 --include 'src/**/*.ts'
Read the groups array: each entry has lines (maximal block length),
occurrences ({ file, startLine, endLine }), and a preview (first 3 lines).
Pick the single group to remediate following these priorities:
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.
- yesterday First seen · 204 lines · 107 tokens per session scan A a589e86a85da
deduplicate-code is a skill published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 2,287 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-26.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
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"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.