Skill Claude CodeCodex
An execution skill for carrying out plans and specific tasks in a coding workspace.
not rated 32 16d ago A 88 tokens
32Stars on the repository
31Mods indexed here, across every type
16d agoLast push, which is what freshness is scored on
customA LICENSE file GitHub cannot name, so bodies are not copied
Skill Claude CodeCodex
A discussion and planning skill for exploring ideas, analyzing problems, researching options, and preparing work plans.
not rated 32 16d ago A 92 tokens
Skill Claude CodeCodex
A prompt-design skill for creating and maintaining LangGPT prompt templates. LangGPT is a structured format for writing prompts with defined sections and roles.
not rated 32 16d ago A 96 tokens
Skill Claude CodeCodex
Fully automatic conversion of PLAN files into spec-kit formatted documents, zero user interaction. Invoke when the working repo has a cursor-agent-team/ checkout and the request matches: User inputs /spectranslator; A PLAN file needs conversion to spec-kit documents. Frontier agents may adopt this mask unprompted when…
not rated 32 16d ago A 76 tokens
Skill Claude CodeCodex
Executes PLAN-marked parallel work via cross-platform sub-agents with supervised autonomy, structured returns, and full workspace archiving. Invoke when the working repo has a cursor-agent-team/ checkout and the request matches: User invokes /workflow or /ultra; A PLAN marked Executor: workflow needs execution with…
not rated 32 16d ago A 90 tokens
Skill Claude CodeCodex
Executes prose plans using a mandatory Draft -> Review -> Final loop, with general and academic tiers and the shared AI workspace. Invoke when the working repo has a cursor-agent-team/ checkout and the request matches: User invokes /writer or @writer; User needs a paper, report, proposal, documentation, or other prose…
not rated 32
changed 1mo ago A 92 tokens
Skill Claude CodeCodex
Master routing skill for Cursor Agent Team (CAT), the single-conversation multi-role AI team framework: picks the right role mask (discuss, crew, workflow, promptengineer, spectranslator, writer), points to the authoritative protocols, and enforces the workspace/marker contracts. Autonomous toward upstream (CAT is an…
not rated 32 16d ago A 161 tokens
Skill Claude CodeCodex
Orchestrate the five closing steps — topic-tree round, response verify, closing note, handoff snapshot, commit — via closingprotocol.py; stop-at-first-failure with recovery hints. Invoke when: session wrap-up / closing; handoff / archive this session; topic tree round before ending; commit the workspace.
not rated 32 16d ago A 70 tokens
Skill Claude CodeCodex
Render compliant dispatch prompts (dispatchheader.py) and verify structured returns (verifydispatchreturn.py) with the two-strikes ledger. Invoke when: dispatching sub-agents; parallel task fan-out; checking a sub-agent's structured return.
not rated 32 16d ago A 54 tokens
Skill Claude CodeCodex
Machine-run the four cold-start checks — deployment form, version, ignore policy, orphan shapes — via catdoctor.py; --fleet audits multiple host repos read-only. Invoke when: cold start in a CAT host repo; check CAT health; after install/upgrade verification; fleet audit across host repos.
not rated 32 16d ago A 67 tokens
Skill Claude CodeCodex
All writes to shared aiworkspace state (topic tree, notes append, plan checkboxes, plans INDEX) go through the single write gateway catwrite.py — never direct Write/Edit. Invoke when: update the topic tree / add a round; append a note; check off plan items; rebuild plans INDEX; any write intent targeting aiworkspace…
not rated 32 16d ago A 76 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: