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/bengous/claude-code-plugins/git-sweepnpx skills add bengous/claude-code-plugins --skill git-sweepgit clone --depth 1 https://github.com/bengous/claude-code-pluginsWhat 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 | $0.00076 | $0.00854 |
| Opus 5 | $0.00038 | $0.00427 |
| Sonnet 5 | $0.00015 | $0.00171 |
| Haiku 4.5 | $0.00008 | $0.00085 |
Grade A, and why
git-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 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Sweep
Route to the correct cleanup phase based on repo state. The phase files
audit.md and apply.md live in this skill's base directory.
Inputs
- base: $ARGUMENTS
(optional: the base branch to audit against, e.g.
/git-sweep dev; empty lets the backend resolve the trunk: git config sweep.base, then origin/HEAD, then main/master/trunk) - branch: !
git branch --show-current - repo: !
git rev-parse --show-toplevel - worktrees: !
git worktree list - pending: !
test -f "$(git rev-parse --absolute-git-dir)/git-sweep-manifest.json" && echo "yes" || echo "no" - tools: !
test -x "${CLAUDE_PLUGIN_ROOT}/scripts/git-clean-audit.ts" && test -x "${CLAUDE_PLUGIN_ROOT}/scripts/git-clean-apply.ts" && echo "ok" || echo "missing"
Routing
if tools == "missing":
STOP — tell user: git-clean-audit and/or git-clean-apply not executable.
Run: chmod +x "${CLAUDE_PLUGIN_ROOT}/scripts/git-clean-audit.ts" "${CLAUDE_PLUGIN_ROOT}/scripts/git-clean-apply.ts"
if pending == "yes":
# A previous run left operations unexecuted (partial failure, or an
# interrupted hand-off). The file holds an already-confirmed selection.
AskUserQuestion:
header: "Manifest"
question: "A pending cleanup manifest exists. Apply it, or re-audit?"
options: "Apply pending manifest (Recommended)"
| "Re-audit (overwrites it)"
if "Apply pending manifest":
Read apply.md and follow it
(do not continue below)
Read audit.md and follow it
The audit phase handles all "nothing to clean" detection itself (local branches, remote branches, worktrees). Do not short-circuit here.
Configuration (git config, all optional)
sweep.base— trunk to audit against when no argument is givensweep.protect(multi-valued) — extra branches never proposed for deletionsweep.unprotect(multi-valued) — lift names from the default protected set (main, master, trunk, dev, develop); the audited base stays protectedsweep.agentPrefix/sweep.backupPrefix— classification prefixes (defaultsworktree-agent-,backup/; they must not overlap)sweep.maxAgeDays— age bound for the containment test (default 180)
What ships with it
2 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.
- yesterday First seen · 85 lines · 76 tokens per session scan A f234a0f85f32
git-sweep is a skill published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 854 once invoked, about $0.0004 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
sql-reporting
Conventions and review steps for writing analytics SQL against the warehouse. Use whenever the task involves querying tables, building a report, or aggregating metrics.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
verify-security
安全校验关卡。自动扫描代码安全漏洞，检测危险模式，确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
n8n:human-like-code-review
Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file. Prioritizes context, architecture fit, solution complexity, bugs, security edge cases, and missing tests. Use when given a PR URL to review, or when the user says /human-like-code-review.