A coordinator for reviewing or executing a user's assigned ClosedLoop work in one project. It can produce a read-only report, or organize related tickets into complete feature deliveries with a plan, code branch, pull request, and testing steps.

Use it to inventory work, group tickets by feature, recover active work, coordinate implementation, and track dependencies and delivery steps.

It gives project work a consistent structure instead of handling every small ticket in isolation. Its report mode also keeps investigation separate from actions that change project records.

cl-sweep — Skill for Claude Code and Codex by closedloop-ai

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.

Any agent

npx skills add closedloop-ai/claude-plugins --skill cl-sweep

Clone the repo

git clone --depth 1 https://github.com/closedloop-ai/claude-plugins

Made for: Claude Code, Codex.

Or install vibe, the plugin that ships this one along with the rest of its 10 skills, 16 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/cl-sweep/github.svg)](https://agentmods.dev/skills/closedloop-ai/claude-plugins/cl-sweep)

Your own site

<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/cl-sweep"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/cl-sweep/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/cl-sweep"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/cl-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 12,103 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00108	$0.12103
Opus 5.5	$0.00043	$0.04841
Sonnet 5.5	$0.00022	$0.02421
Haiku 4.5	$0.00011	$0.01210

Measured yesterday against content hash 677a93c95dc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cl-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.

The scan reads SKILL.md. This mod also ships 28 executable files (scripts/activity-display.test.mjs, scripts/app-server-worker-recovery.black-box.test.mjs, scripts/app-server-worker-session.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/vibe/skills/cl-sweep/SKILL.md · 766 lines

How it starts

The opening of the file, as written. The whole thing — 766 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CL Sweep

Purpose

Produce a read-only project work report, or act as the root coordinator for all actionable assigned ClosedLoop work in one project. In execution mode, keep every issue as its own record while treating each selected complete functional page or capability as one scheduling and delivery unit: one execution owner, worktree, branch, combined plan, PR, manual-QA plan, and terminal reconciliation.

Report-Only Route

If the user asks only for an inventory, report, feature grouping, blocker ownership, or reassignment advice, read and follow ../cl-work-report/SKILL.md immediately and stop after returning its private report. Do this before Execution Surface Selection, Project-Keyed Root Recovery, get_goal, state-root creation, leases, workers, status changes, reassignment, comments, or any other mutation. A report recommendation never authorizes execution or reassignment.

Display activity

For participating Desktop and CLI owners, follow display events at actual activity boundaries and existing dispatch/PR verification points. Display metadata never changes lifecycle or permissions, but activity publication is a required dispatch invariant: every new CLI worker turn must declare --activity-phase planning|coding|reviewing; reviewing must also declare --review-kind plan|code. The managed worker runtime records the phase after App Server accepts the turn and exposes currentActivity.recorded in status. A scheduling or status pass is incomplete while an active owner has no current activity or recorded is false; repair the exact declared phase before reporting or launching more work. After existing authenticated ClosedLoop reads, publish the observed business status using the same reference; do not add queries for the wallpaper. Report explicit ticket dependencies and their explicit resolution through that reference; never infer edges from waiting.

Shared Policy

Before querying tickets, routing blockers, writing blocker comments, sending direct messages, or creating the parent goal text, read the sibling policy skill at ../cl-policy/SKILL.md and follow its Required Reference resolution order. Use ../cl-policy/references/local-policy.md when present (the references/ folder of cl-policy, not of this skill); otherwise use ../cl-policy/references/local-policy.example.md only to understand the required shape, then require a populated $HOME/.closedloop-ai/local-policy.md before routing. Use the policy terms Product contact, Engineering attention contact, and Sweep owner; do not hardcode a personal name for the engineering attention contact in prompts, memory fields, or communication text.

Read the full file on GitHub · 766 lines

Files

What ships with it

44 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.

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.

yesterday Changed · +1 lines 677a93c95dc6
4d ago First seen · 765 lines · 108 tokens per session scan A cccf7cb51abf

Subscribe to this mod's changes

cl-sweep is a skill published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 108 tokens to every session and 12,103 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 2026-10-06.

Claude Code LLM Project management agentic-ai ai-agents anthropic developer-tools

file-a-task

File work into nohuman (taskadd) and check on it (taskstatus) via the nohuman MCP bridge, instead of doing the work inline.

no-human-ai/no_human · 37 tokens

fleet

The session roster (/foundry:fleet) — native /list-agents annotated with each row's foundry programme, over the NATIVE session/container list. Read-only/advisory. Trigger to see all your parallel sessions and containers at a glance with their foundry context, or when supervising many sessions and asking "what is each…

lukasrepublic/agentic-foundry · 73 tokens

parallel-feature-development

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…

wshobson/agents · 105 tokens

bazel-build-optimization

Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.

wshobson/agents · 36 tokens

company-ceo

Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.

Prism-Shadow/penguin-harness · 56 tokens

sdlc-accelerate

End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.

jmagly/aiwg · 23 tokens