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 skills add closedloop-ai/claude-plugins --skill cl-work-reportgit clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWrote 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/closedloop-ai/claude-plugins/cl-work-report)<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/cl-work-report"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/cl-work-report/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/closedloop-ai/claude-plugins/cl-work-report"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/cl-work-report.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 | $0.00076 | $0.05071 |
| Opus 5.5 | $0.00030 | $0.02028 |
| Sonnet 5.5 | $0.00015 | $0.01014 |
| Haiku 4.5 | $0.00008 | $0.00507 |
Grade A, and why
cl-work-report 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClosedLoop Work Report
Purpose
Build a current, complete inventory of the requesting user's assigned work in one ClosedLoop project. Group it into concrete page or capability features with bounded user journeys and acceptance outcomes, using PRDs and plans as supporting evidence rather than grouping boundaries. Trace upstream dependencies and recommend ownership changes only when live evidence shows transfer is better than coordination.
The report is private. Create a local HTML report by default and return its link with a concise response summary. Use Markdown only when the user explicitly requests plain text or HTML rendering is unavailable; disclose that limitation and never claim a diagram rendered when it did not.
Boundaries
- This skill is read-only. Never reassign tickets, update statuses or relationships, post comments, send messages, create loops or goals, acquire leases, launch workers, implement work, or change PRs.
- Read
../cl-policy/SKILL.mdfor ClosedLoop access and fallback rules. A private report does not require configured Product or engineering contact names and must not stop merely because communication policy is unavailable. - Load
closedloop-intelby name ($closedloop-intelin Codex or/closedloop-core:closedloop-intelin Claude Code). Discover the read-onlyclosedloop-graphserver by capability, call itsget_routing_protocolfirst, and follow the live route and evidence rules it returns. Never hardcode an MCP server prefix. - Graph results are discovery evidence. Live ClosedLoop is authoritative for the current user, project, assignment, status, and relationship direction.
- A document whose type is
FEATUREmay be an ordinary ticket. Do not assume its type makes it a product-feature parent or execution-unit boundary. - Keep the complete product-feature or PRD universe separate from the user's selected delivery units. A selected delivery unit is the narrowest evidence-backed, independently functional outcome containing one or more of the user's assigned tickets. Its required shipping changes land in one PR. Shared prerequisites may remain externally owned and land first; design evidence need not enter the PR. Explicitly post-rollout cleanup remains mandatory follow-up work and must not be forced into a pre-rollout PR. Do not turn every sibling under a broad feature or PRD into the user's execution scope.
What ships with it
7 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 Changed 3f586040e712
- 4d ago First seen · 148 lines · 76 tokens per session scan A 87d55e2521ad
cl-work-report is a skill published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 5,071 once invoked, about $0.0003 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.
Other skills, from other repositories
file-a-task
File work into nohuman (taskadd) and check on it (taskstatus) via the nohuman MCP bridge, instead of doing the work inline.
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…
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…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
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.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.