sweep

A maintenance skill that dispatches several smaller cleanup tasks for worktrees, branches, plans, tests, and issues. A worktree is a separate checkout of a Git repository, and a branch is a line of development.

In plain words
What is it for?
Use it for periodic maintenance, either to preview cleanup with a dry run or to apply the cleanup.
Why use it?
It helps find and remove leftover development state that is no longer needed.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/nirecom/agents/sweep
Any agent
npx skills add nirecom/agents --skill sweep
Clone the repo
git clone --depth 1 https://github.com/nirecom/agents

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 747 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00747
Opus 5 $0.00020 $0.00374
Sonnet 5 $0.00008 $0.00149
Haiku 4.5 $0.00004 $0.00075

Measured 2d ago against content hash c04f9295ed7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sweep 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 2d 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.

skills/sweep/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hub skill for periodic maintenance sweeps. Dispatches to one or more sub-skills that each reclaim a specific class of residual state. A flagless run applies (deletes); pass --dry-run to preview without writing.

Procedure

SW-0. Emit echo <<WORKFLOW_ENFORCE_WORKTREE_OFF: sweep hub — maintenance writes/deletes across sub-skills>> before SW-1. SW-1. Invoke /sweep-worktrees (deletes by default; pass --dry-run to preview). SW-2. Invoke /sweep-branches (deletes by default; pass --dry-run to preview). Capture stdout for post-processing (SW-2b/SW-2c). SW-2b. Parse sweep-branches stdout for WORKTREE-LOCKED lines. Each WORKTREE-LOCKED: branch=X wt=<path> line triggers: git -C "$MAIN_ROOT" worktree remove --force "<path>" 2>/dev/null || true This step lives in the hub (not sweep-branches.sh) because the hub has worktree-remove authority; sweep-branches.sh does not. SW-2c. After worktree removal, retry git branch -D for each WORKTREE-LOCKED branch using the branch=X field. SW-2b removes the worktree block, so the cascade rule no longer prevents deletion. Failures are ignored (reclaimed next cycle). SW-3. Invoke /sweep-plans (deletes by default; pass --dry-run to preview). SW-4. Invoke /sweep-tests (deletes by default; --dry-run and --fix-headers are forwarded when passed). SW-5. Invoke /sweep-issues (tier-1 meta-parent closes apply by default; --dry-run previews). Tier-2 candidates are human-gated and only surface under --deep. SW-6. Emit echo <<WORKFLOW_ENFORCE_WORKTREE_ON: sweep hub complete>> after SW-5, regardless of outcome. SW-7. Future sub-skills to be added in subsequent PRs:

  • /sweep-wip — stale WIP fingerprints
  • /sweep-logs — old terminal logs / temp files

Forward --dry-run (and any other flags) to each invoked sub-skill verbatim.

Rules

  • Each sub-skill is independent; one failure does not stop the chain.
  • A flagless run deletes; pass --dry-run to preview. --apply remains accepted as an explicit synonym of the default.
  • Both the nightly cron (.github/workflows/sweep.yml) and manual /sweep use this hub.
  • The nightly cron acts as a workflow health check; zombie reclamation primarily relies on manual /sweep on the developer's machine, since CI runners do not see local worktrees.
  • Never pass --force — none of the sub-skills accept it by design.
  • Never add --deep automatically for /sweep-issues; it is for human sessions only, so cron and hub runs never stop at a tier-2 gate.

Read the full file on GitHub · 48 lines

Changes

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.

  1. 2d ago First seen · 48 lines · 40 tokens per session scan A c04f9295ed7a

Subscribe to this mod's changes

sweep is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 747 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 2026-08-31.

Related

Other skills, from other repositories

nemoclaw-contributor-implement-issue

Implement an accepted NemoClaw GitHub issue in the current checkout. Use when a user asks to pick up an issue for implementation, implement or fix a named issue, or add the issue's tests. Confirm accepted scope, deliver the smallest independently valuable capability slice, and record validation and remaining gates…

NVIDIA/NemoClaw · 134 tokens

amazon-bestseller-listing

Amazon Best Sellers listing scraper: extract product cards from any Amazon Best Sellers (zgbs) or /gp/bestsellers/ category page — returns rank (position on chart), asin, title, url, image, imageAlt, price, stars, reviewCount, ratingRaw per item, plus category metadata (categoryName, categoryFullName, categoryUrl) and…

browser-act/skills · 300 tokens

amazon-reviews-api-skill

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…

browser-act/skills · 124 tokens

amazon-competitor-analyzer

Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.

browser-act/skills · 48 tokens

cabloy-worktree-environment

This skill must be used only when the user explicitly invokes /cabloy-worktree-environment or explicitly asks to perform the named Cabloy worktree-environment setup. It prepares a confirmation-gated, worktree-local Vona and Zova runtime environment for a linked Cabloy Basic or Cabloy Start Git worktree using Git…

cabloy/cabloy · 126 tokens

shopify-hydrogen

Hydrogen storefront implementation cookbooks. Some of the available recipes are: B2B Commerce, Bundles, Combined Listings, Custom Cart Method, Dynamic Content with Metaobjects, Express Server, Google Tag Manager Integration, Infinite Scroll, Legacy Customer Account Flow, Markets, Partytown + Google Tag Manager…

Shopify/Shopify-AI-Toolkit · 106 tokens