OWASP Top 10 Testing with Strix
usestrix/strix
Runs Strix's autonomous exploit agents against each OWASP Top 10:2025 category and the API Security Top 10, reporting only what could actually be proven with a proof-of-concept.
Split one top-level high-complexity ClosedLoop feature ticket into smaller executable child tickets when safe.
$ npx skills add closedloop-ai/claude-plugins --skill cl-split -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install closedloop-ai/claude-plugins cl-split --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/code/skills/cl-split .claude/skills/cl-split && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cl-split" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/cl-split into .claude/skills/cl-split/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cl-split", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/cl-splitType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add closedloop-ai/claude-plugins --skill cl-split -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install closedloop-ai/claude-plugins cl-split --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/code/skills/cl-split .agents/skills/cl-split && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cl-split" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/cl-split into .agents/skills/cl-split/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cl-split", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add closedloop-ai/claude-plugins --skill cl-split -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install closedloop-ai/claude-plugins cl-split --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/code/skills/cl-split .cursor/skills/cl-split && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cl-split" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/cl-split into .cursor/skills/cl-split/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cl-split", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/closedloop-ai/claude-plugins.git --path plugins/code/skills/cl-split--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add closedloop-ai/claude-plugins --skill cl-split -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install closedloop-ai/claude-plugins cl-split --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/code/skills/cl-split .gemini/skills/cl-split && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cl-split" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/cl-split into .gemini/skills/cl-split/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cl-split", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install closedloop-ai/claude-plugins cl-splitInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add closedloop-ai/claude-plugins --skill cl-split -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/code/skills/cl-split .github/skills/cl-split && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cl-split" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/cl-split into .github/skills/cl-split/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cl-split", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add closedloop-ai/claude-plugins --skill cl-split -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install closedloop-ai/claude-plugins cl-split --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/code/skills/cl-split .opencode/skills/cl-split && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cl-split" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/cl-split into .opencode/skills/cl-split/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cl-split", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
cl-splitSplit one top-level high-complexity ClosedLoop feature ticket into smaller executable child tickets when safe.
Cl Split is an agent skill from closedloop-ai/claude-plugins. Split one top-level high-complexity ClosedLoop feature ticket into smaller executable child tickets when safe. Use when $cl-analyze or $cl-sweep determines a top-level ticket is HIGH complexity but potentially splittable, or when asked to decompose a FEA- ticket before execution. Keep engineering/split automation details private; recommend a company-visible comment only for a genuine Product decision under cl-policy or when the user explicitly requests the exact comment. Enforce one split level only; do not split…
Its SKILL.md is about 5.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
The repository describes itself as: Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase… The licence is Apache-2.0.
12 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 476b54c. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
codexFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Cl Split loads about 5.4k tokens when it runs. Until then it costs about 144 tokens; SKILL.md has 2,531 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from closedloop-ai/claude-plugins at commit 476b54c, republished under its Apache-2.0 licence (© closedloop-ai). 2,531 words, ~5,400 tokens.
.claude/skills/cl-split/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Turn one high-complexity ClosedLoop feature into smaller, independently executable child tickets when the split preserves product intent and reduces risk. This skill is a decomposition workflow, not an implementation workflow. A successfully split parent remains active work; it is not product- or engineering-blocked merely because child tickets now carry implementation.
Before routing split concerns or recommending blocker communication, 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.
$cl-execute from this skill.$cl-split invocation is approval for that narrow decomposition action.CHILD_EXECUTION_ONLY when the child should be analyzed/executed directly, or SPLIT_REPAIR_REQUIRED only when the child is not execution-sized because the original split shape is defective.BLOCKED. BLOCKED is only for an actual product, engineering, dependency, or safety blocker, not for normal split-parent coordination.DONE until all implementation child tickets are done and the parent acceptance criteria are covered.EXTREME risk work. Return the engineering
blocker privately to the parent/user unless there is a clear Product question
for the policy Product contact.SPLIT_CREATED unless every child ticket is assigned to the sweep user or otherwise visible to the sweep, and is in an actionable status the sweep will pick up.DIRECT_EXECUTION_RECOMMENDED without creating tickets. Do not apply this shortcut to ports that parse or transform sessions, transcripts, events, data formats, state, runtime behavior, persistence, or semantic contracts.$workflow-orchestrator, $workflow-execute, or any orchestrator-run ticket execution workflow.closedloop-graph MCP proactively under cl-policy
host-capability rules
before proposing, repairing, or creating a split. Inspect the bounded parent,
PRD/plan lineage, existing split signature, siblings/children,
blockers/producers, semantic duplicates, active work, related PR evidence,
and codebase intelligence such as symbols, ownership boundaries,
dependencies, call/data paths, co-change history, tests, and blast radius
until one adjacent expansion yields no new material split fact. Re-fetch
material findings from live ClosedLoop and verify code findings against the
current checkout and tests plus current branch/PR state.
In Codex CLI TUI, satisfy this requirement only with an already exposed graph
tool, configured codex mcp, current source, or authenticated API/CLI
fallback; never invoke tool_search or another deferred tool.
Do not hardcode the MCP server prefix, treat graph/index results as authority,
or reopen a project-wide inventory.A high-complexity ticket is splittable only when all of these are true:
$cl-sweep may later place
compatible ready children in one merge batch when their implementation,
review, validation, rollback, and merge policies align.Do not split when the ticket is mostly ambiguous requirements, a single atomic migration, a security/billing/permission change needing architecture review, or a broad rewrite without a safe intermediate milestone.
FEA-* slug.closedloop-graph under cl-policy host-capability rules to validate the bounded lineage, dependency, duplicate, active-work, related-PR, and codebase architecture set, including ownership, call/data paths, tests, co-change evidence, and blast radius. In Codex CLI TUI, use an already exposed graph tool or the documented CLI/source fallback and never emit a dynamic tool call. Verify code findings against the current checkout. Treat the input as a split child only when split-specific evidence exists: split signature, $cl-split child text, parent split comment, or a PRODUCES relationship showing the ticket was produced by a split. A generic parent link alone is not enough; classify lineage as unknown and investigate before refusing top-level splitting. If the input is a split child, identify the original top-level parent when possible and do not create tickets.$cl-analyze result in the thread if present. If missing or stale, inspect enough ticket/repo context to classify split feasibility.HIGH classification. Separate files likely to change from context/dependencies that only need inspection or preservation. If one coherent referential harness registration, wrapper, link, manifest, or dispatch-only adapter plus its focused tests and documentation satisfies the ticket without translating behavior or contracts, stop without creating tickets and return DIRECT_EXECUTION_RECOMMENDED. Ports involving semantic or data-flow transformation must still be classified from their actual implementation boundaries.CHILD_EXECUTION_ONLY unless the current $cl-analyze result or fresh inspection proves SPLIT_REPAIR_REQUIRED.SPLIT_CREATED with the existing child URLs instead of creating duplicates. If matching children already exist but one or more are not execution-sized, continue to the repair step instead of treating the existing split as successful.SPLIT_CREATED: Child tickets were created or updated in ClosedLoop and linked/commented back to the parent.DIRECT_EXECUTION_RECOMMENDED: The top-level input is execution-sized after separating actual implementation mutations from contextual/dependency surfaces. No child tickets were created; the parent coordinator must rerun $cl-analyze with the corrected scope before execution.CHILD_EXECUTION_ONLY: The input is already a split child that must not be split again and should be returned to $cl-analyze/$cl-execute as a direct execution candidate.SPLIT_PROPOSED: A safe split exists, but child ticket creation was unavailable or explicitly needs human creation.PRODUCT_DECISION_REQUIRED: Product input is needed before child tickets can be valid.SPLIT_REPAIR_REQUIRED: The input is already a split child that is not execution-sized because the original split shape is defective, and the parent orchestrator must switch context back to the original parent split. Do not create grandchildren.ENGINEERING_REVIEW_REQUIRED: The engineering attention contact must review architecture/risk before splitting or executing.NOT_SPLITTABLE: The parent should remain blocked for manual review.SPLIT_REPAIR_REQUIRED. Before repairing, inspect sibling child statuses, workflow memory records, active Codex threads, branches, and PRs. Do not supersede or rewrite active child work automatically. Preserve active children and repair around them by creating or updating non-overlapping sibling tickets when safe; if active work makes safe repair impossible or human product/architecture input is required, keep the engineering details private and surface the decision to the user, using a Product comment only for an independently actionable Product question. Update or replace only inactive/obsolete one-level child tickets under the same parent and split signature. Do not create grandchildren. Do not leave overlapping or obsolete children actionable; use relationships and the project's supported non-actionable status rather than public recordkeeping comments. Return SPLIT_CREATED after a successful repair with the updated child set.FEA-* tickets in the same project with TODO status by default, assigned to the policy Sweep owner unless project conventions require a different assignee. Use BACKLOG only when the project convention treats BACKLOG as sweep-actionable. Do not create children in TRIAGE, IN_PROGRESS, IN_REVIEW, or BLOCKED. If a child cannot be assigned to the sweep user, cannot be put in TODO or sweep-actionable BACKLOG, or cannot be made visible in the sweep queue, return SPLIT_PROPOSED or ENGINEERING_REVIEW_REQUIRED instead of SPLIT_CREATED.SPLIT_PROPOSED; do not publish an engineering comment or DM without exact user authorization.SPLIT_CREATED, preserve child links and split signature through first-class relationships, ticket fields/statuses, and private workflow memory; do not add parent recordkeeping comments. Mark the parent IN_PROGRESS when child implementation work exists or will be picked up by the sweep. If the parent is already BLOCKED only because of an older split-parent convention, correct it to IN_PROGRESS. Leave the parent unchanged only when status mutation is unavailable, and record why privately in the result. Reserve BLOCKED for SPLIT_PROPOSED, PRODUCT_DECISION_REQUIRED, ENGINEERING_REVIEW_REQUIRED, NOT_SPLITTABLE, invisible/unassigned children, or a real blocker unrelated to the successful split itself.Each child ticket must include:
TODO, or BACKLOG only when documented as sweep-actionable for the project.$cl-analyze result before batching.Human UI plan approval required before plan approval, feature status mutation, branch creation, code changes, PR work, or merge work when missing.Prefer two to five child tickets based on genuine implementation boundaries,
not desired PR count. If more than five are needed, mark
ENGINEERING_REVIEW_REQUIRED unless the parent is obviously an epic and project
conventions support that many children. A successful split does not force the
sweep to serialize one PR through the merge queue for every child.
SPLIT_CREATED: No blocker comment or DM is required. $cl-sweep should record the parent as split and then re-query assigned tickets so the new children can be analyzed normally.DIRECT_EXECUTION_RECOMMENDED: No blocker comment or DM is required. $cl-sweep should rerun $cl-analyze for the top-level ticket with the corrected expected-touched-surface scope and must not create child tickets from the rejected split.CHILD_EXECUTION_ONLY: No blocker comment or DM is required. $cl-sweep should re-run $cl-analyze for the child as a direct execution candidate and must not call $cl-split on that child again.SPLIT_REPAIR_REQUIRED: No blocker or recordkeeping comment is required. $cl-sweep should repair the original parent split through relationships/statuses and private durable artifacts, then re-query assigned tickets.SPLIT_PROPOSED: Keep the child drafts and failure reason in the private result/memory and surface them to the user. Do not post a ticket comment or DM without exact user authorization.PRODUCT_DECISION_REQUIRED: Add a first-person ClosedLoop comment tagging the policy Product contact with the parent ticket, the product decision needed, and the proposed split if useful. Do not use Slack.ENGINEERING_REVIEW_REQUIRED or NOT_SPLITTABLE: Keep risk/evidence private and surface it to the invoking user. ClosedLoop comment target is none unless the user explicitly requests the exact comment.When invoked by $cl-sweep, the parent owns Product-decision comments and private workflow-memory recording. Engineering/operational comments and DMs remain forbidden unless the user explicitly authorized the exact communication.
When a parent task id was supplied, send the parent the completed
CL Split Result before ending the turn. On Desktop, use the statically
available send_message_to_thread. In a cwd-bound CLI worker, emit the matching
current-generation CL_SWEEP_EVENT v1 as the final line for the managed App
Server runner to persist and deliver; never dynamically invoke parent messaging
from TUI. The callback is required for every outcome and must
include the input/parent ticket, this task id when available, outcome, child
set or blocker, and exact next parent action. Do not rely on a child final
response or parent polling to communicate completion. Retry one failed callback
once, then include the exact callback failure in the result.
End with this structure:
## CL Split Result
Input ticket: <FEA slug and URL>
Parent ticket: <FEA slug and URL>
Original split parent: <top-level parent FEA/url when input is a split child, or same as Parent ticket>
Project: <ClosedLoop project slug/name and URL>
Repo: <repo name or unknown>
Split lineage: <top_level | split_child | unknown>
Outcome: <SPLIT_CREATED | DIRECT_EXECUTION_RECOMMENDED | CHILD_EXECUTION_ONLY | SPLIT_PROPOSED | SPLIT_REPAIR_REQUIRED | PRODUCT_DECISION_REQUIRED | ENGINEERING_REVIEW_REQUIRED | NOT_SPLITTABLE>
Confidence: <LOW | MEDIUM | HIGH>
Parent status recommendation: <IN_PROGRESS | leave unchanged | ask engineering attention contact | BLOCKED only for real blocker>
Split signature: <stable signature from parent and child fields>
Summary:
- <one to three bullets>
Split rationale:
- <why this split does or does not preserve product intent and reduce risk>
Child tickets:
- <created, reused, updated, superseded, or draft FEA/url/title>: <assignee, status, objective, acceptance criteria summary, dependencies, validation, ui_design_source: not_applicable | design | screenshot | prototype | missing, human_ui_plan_approval: not_required | required>
Existing related work:
- <duplicates, active PRs, existing child tickets, or none>
Parent update:
- <comment/link result, parent status result, legacy BLOCKED correction if any, or reason parent was left unchanged>
Communication:
- ClosedLoop comment target: <none | product contact>
- Engineering attention DM: <not_required | explicitly_user_authorized>
- Recommended ClosedLoop comment: <ready-to-post concise first-person comment, or none>
- Recommended engineering attention DM: <ready-to-send only when explicitly user-authorized, otherwise none>
Persistence:
- Parent memory state: <SPLIT_CREATED | DIRECT_EXECUTION_RECOMMENDED | CHILD_EXECUTION_ONLY | SPLIT_PROPOSED | SPLIT_REPAIR_REQUIRED | SPLIT_BLOCKED>
- Parent memory key: cl_sweep_ticket_state <project_slug_or_url> <parent FEA-slug>
- Child ticket slugs/URLs: <created or reused child tickets, assignees, statuses>
- Child memory keys: <cl_sweep_ticket_state entries to query next, or none>
- Recheck when: <specific parent/product/engineering change that should trigger re-analysis, or none>
Next parent action:
- <re-query assigned tickets | re-analyze top-level ticket for direct execution | re-analyze child for execution | repair original parent split | add ClosedLoop comment tagging product contact | surface engineering blocker privately to user | manual intervention>© closedloop-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in plugins/code/skills/cl-split of closedloop-ai/claude-plugins.
Open the folder on GitHubat commit 476b54c
Cl Split next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cl Split this skillclosedloop-ai/claude-plugins | 122 | — | ~5.4k | Automated safety check: Pass | Apache-2.0 | |
| OWASP Top 10 Testing with Strixusestrix/strix | 67k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Code Splittingthedaviddias/Front-End-Checklist | 74k | — | ~492 | Automated safety check: Pass | MIT | |
| Splitting Oversized ModulesPostHog/posthog | 40k | — | ~2.2k | Automated safety check: Pass | Custom licence | |
| Complexity Cutssickn33/agentic-awesome-skills | 47k | 1 repos | ~3.8k | Automated safety check: Pass | Apache-2.0 | |
| SplitsBankrBot/skills | 1.2k | — | ~3.9k | Automated safety check: Pass | None |
usestrix/strix
Runs Strix's autonomous exploit agents against each OWASP Top 10:2025 category and the API Security Top 10, reporting only what could actually be proven with a proof-of-concept.
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing large SPA bundles, new dependency additions, or routes that feel slow to hydrate.
PostHog/posthog
Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior.
sickn33/agentic-awesome-skills
Lower Big-O on existing code via a one-transformation-at-a-time playbook with verify-revert-stop.
BankrBot/skills
Use Splits with Bankr for onchain treasury operations: secure assets, process revenue, manage operating subaccounts, pay expenses, govern contracts, and maintain clean accounting books.
github/awesome-copilot
Refactor given method ${input:methodName} to reduce its cognitive complexity to ${input:complexityThreshold} or below, by extracting helper methods.
closedloop-ai/claude-plugins
Run Codex to review a plan file and return structured feedback with a verdict.
closedloop-ai/claude-plugins
Check if critic reviews are still valid before re-running Phase 2.5 critics.
closedloop-ai/claude-plugins
Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches.
closedloop-ai/claude-plugins
Check for a cached plan-evaluation.json result before launching the plan-evaluator agent.
closedloop-ai/claude-plugins
This skill should be used when needing to locate files within the Claude Code plugins cache directory (~/.claude/plugins/cache).
closedloop-ai/claude-plugins
Start a detached GitHub pull-request monitor that wakes the exact launching Codex Desktop or CLI root through the managed Codex App Server when review, CI, conflict, merge-queue, closure, readiness…
Split one top-level high-complexity ClosedLoop feature ticket into smaller executable child tickets when safe. Cl Split is an agent skill from closedloop-ai/claude-plugins. Split one top-level high-complexity ClosedLoop feature ticket into smaller executable child tickets when safe.
Cl Split fits situations like: $cl-sweep determines a top-level ticket is HIGH complexity but potentially splittable; asked to decompose a FEA- ticket before execution; explicitly requests the exact comment.
Run `npx skills add closedloop-ai/claude-plugins --skill cl-split -a claude-code`. Or copy the skill folder (plugins/code/skills/cl-split in closedloop-ai/claude-plugins) into .claude/skills/cl-split in your project. Claude Code loads it when a task matches its description.
Run `npx skills add closedloop-ai/claude-plugins --skill cl-split -a codex`. Or copy the skill folder (plugins/code/skills/cl-split in closedloop-ai/claude-plugins) into .agents/skills/cl-split in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add closedloop-ai/claude-plugins --skill cl-split -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cl-split, .gemini/skills/cl-split, .github/skills/cl-split and .opencode/skills/cl-split in your project.
Going by SKILL.md and its folder, Cl Split needs the command-line tools its instructions call (codex).
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Cl Split is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.4k tokens (SKILL.md is roughly 22k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Cl Split: OWASP Top 10 Testing with Strix (usestrix/strix, 67k stars), Code Splitting (thedaviddias/Front-End-Checklist, 74k stars), Splitting Oversized Modules (PostHog/posthog, 40k stars) and Complexity Cuts (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
closedloop-ai (a GitHub organization) maintains it in closedloop-ai/claude-plugins, which has 122 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 7, 2026.
Source: closedloop-ai/claude-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.