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 agentmods add skills/besimple-oss/broccoli/dedupnpx skills add besimple-oss/broccoli --skill dedupgit clone --depth 1 https://github.com/besimple-oss/broccoliWrote 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/besimple-oss/broccoli/dedup)<a href="https://agentmods.dev/skills/besimple-oss/broccoli/dedup"><img src="https://agentmods.dev/badge/skills/besimple-oss/broccoli/dedup.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 | $0.00032 | $0.01555 |
| Opus 5 | $0.00016 | $0.00777 |
| Sonnet 5 | $0.00006 | $0.00311 |
| Haiku 4.5 | $0.00003 | $0.00155 |
Grade A, and why
dedup 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 6d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dedup Loop (dedupe-only)
Input: a git base SHA/ref to dedupe against.
Default/recommended is auto, which resolves a branch-wide merge-base from integration/default refs first, then falls back to upstream (@{u}).
Preconditions
- Confirm you are in the intended repo:
git rev-parse --show-toplevel - Ensure you have a branch-wide base commit SHA (the fork-point/common-ancestor with the integration branch).
- Start from a clean working tree (required):
git status --porcelainshould be empty.
- Ensure git can create commits (stop if missing):
- If commits fail due to missing identity, configure
user.nameanduser.email.
- If commits fail due to missing identity, configure
- Ensure both CLIs are available (
codexandclaude) because reviewer/responder must be different vendors.
Scope / intent
- This is NOT a general code review.
- Only act on:
- duplicate code introduced/expanded by
BASE_SHA..HEAD, and/or - code introduced by
BASE_SHA..HEADthat reimplements an existing shared util already in the repo.
- duplicate code introduced/expanded by
- Do not apply unrelated fixes (style, perf, security, naming, error handling) unless strictly required to complete a dedupe/reuse change safely.
Expected runtime
Typically runs 10–30 minutes, but allow at least 60 minutes.
Do not interrupt/restart the subagent if it looks stuck. The loop script owns stuck/timeout handling and will exit on its own when it completes or when --timeout is reached. Prefer watching the periodic heartbeat output (--heartbeat-seconds) instead of tailing logs.
Why Claude sometimes looked “stuck”
Claude Code print mode can be silent in --output-format text until it finishes (including during tool work). This repo defaults Claude subprocesses to --output-format stream-json --include-partial-messages so the wrapper sees measurable progress and inactivity timeouts mainly trigger on true hangs.
Run
resolve_skill_dir() {
local name="$1"
local repo_root=""
repo_root="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
local candidates=(
"$repo_root/.agents/skills/$name"
"$repo_root/.claude/skills/$name"
"$HOME/.agents/skills/$name"
"$HOME/.codex/skills/$name"
"$HOME/.claude/skills/$name"
)
for d in "${candidates[@]}"; do
if [[ -d "$d" ]]; then
echo "$d"
return 0
fi
done
echo "Error: skill '$name' not found in repo-scoped or user-scoped skill dirs." >&2
return 1
}
DEDUP_SKILL_DIR="$(resolve_skill_dir dedup)"
python3 "$DEDUP_SKILL_DIR/scripts/run_dedup_loop.py" auto
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 114 lines · 32 tokens per session scan A cbf72162d752
dedup is a skill published in the GitHub repository besimple-oss/broccoli (285 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,555 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 2026-08-30.
Other skills, from other repositories
submit-review
Reference for how a finished ticket reaches human review in the Gaffer factory. Submission is RUNNER-OWNED — the agent commits its work and evidences the ACs, then stops; the runner records the delivery, pushes, opens the PR, and submits for review. Invoke when you think your work is ready to hand off, to confirm what…
high-quality-commit
コード変更を適切なgitコミット戦略でgit commitします。基本的には既存のgitコミットへのsquash戦略を採用し、必要に応じてブランチ全体のgitコミット履歴を再構成します。実装完了時やユーザーがgit commitを依頼した時に使用します。.
agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
git-commit
Stage, write, and structure git commits and pull requests cleanly. Read this before committing — for conventional-commit message format, when to split commits, and how to open a PR with the gh CLI.
commit-and-push
Create a well-formatted git commit and push to remote repository.