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-find-related-ticketsgit 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-find-related-tickets)<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/cl-find-related-tickets"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/cl-find-related-tickets/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-find-related-tickets"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/cl-find-related-tickets.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 | $0.00131 | $0.02528 |
| Opus 5.5 | $0.00052 | $0.01011 |
| Sonnet 5.5 | $0.00026 | $0.00506 |
| Haiku 4.5 | $0.00013 | $0.00253 |
Grade A, and why
cl-find-related-tickets 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 4d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find Related ClosedLoop Tickets
Understand the code blast area before searching ClosedLoop. Then find relevant work without treating project, assignee, title, or age as a reliable scope boundary. Search broadly, verify narrowly, and return a concise report.
Inputs
Extract these from the request when present:
- Area of concern: required. Accept product behavior, page, route, component, service, schema, API, workflow, ticket, PR, or incident.
- Repository or local checkout: optional input, but required to claim a code-grounded exhaustive result for an implementation concern. Resolve it from anchor metadata when omitted.
- Anchor artifacts: optional ticket, PRD, plan, PR, branch, file, or route.
- Known ticket set: optional. When supplied, report only newly discovered tickets unless the user requests the full inventory.
- Cutoff: optional. Use it to distinguish tickets that existed before and after a freeze or decision.
- Assignee or project filters: optional. Treat them as requested restrictions only; otherwise search all assignees and projects.
- Terminal-status inclusion: optional. Exclude completed and canceled issues by default.
Ask one concise clarification when the implementation repository or area cannot be resolved from the request, anchor metadata, or available checkouts. Do not replace the required code pass with guessed search terms.
Safety
Remain read-only.
- Do not create or update documents, comments, relationships, statuses, goals, loops, branches, code, or PRs.
- Do not invoke execution, split, or blocker-routing workflows.
- Do not write workflow repo memory unless the user separately requests persistence.
- Never hardcode a ClosedLoop MCP tool prefix. The prefix depends on the user's local MCP connection name.
- Follow
cl-policyhost-capability rules when discovering ClosedLoop tools. Usetool_searchonly when the current host explicitly supports dynamic calls. In Codex CLI TUI, use already exposed MCP tools or the documentedcodex mcp, CLI/source, or authenticated API fallback. The TUI must not calltool_searchmerely to satisfy the graph requirement. - Discover and use the read-only
closedloop-graphMCP as the primary indexed discovery surface for ticket/PRD/plan lineage, dependencies, semantic matches, duplicates, PR overlap, and codebase intelligence including symbols, files, ownership boundaries, dependencies, call/data paths, co-change history, tests, and blast radius. Treat graph results as candidates only; re-fetch every reported ticket and material relationship from live ClosedLoop and verify code/PR claims against current repository and GitHub state. Use graph code intelligence to establish the implementation blast area, not only to search the ticket corpus. Never emit a dynamic graph tool call from Codex CLI TUI. - If the available connection cannot support an organization-wide search, state the uncovered boundary and do not call the result exhaustive.
What ships with it
1 file 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.
- 4d ago First seen · 190 lines · 131 tokens per session scan A 8f8b18a4ec45
cl-find-related-tickets is a skill published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 131 tokens to every session and 2,528 once invoked, about $0.0005 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.