Skill Claude CodeCodex
Deterministic self-evaluation rubric for decision escalations — scored every run using the FRAME framework.
not rated 142 2d ago A 24 tokens
original MIT
142Stars on the repository
23Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
agent-memory
02Skill Claude CodeCodex
Long-term and session memory across sessions.
not rated 142 2d ago A 11 tokens
original MIT
Skill Claude CodeCodex
Builds the design tree for the grill — decisions mapped as nodes with dependencies, recommendations, and impact, pruned by path.
not rated 142 2d ago A 30 tokens
original MIT
Skill Claude CodeCodex
Grounds the grill's settled decisions in the codebase — annotates impl.md with file paths, signatures, reference files, test specs, and LOC; re-grounds the next epic after each landing.
not rated 142 2d ago A 47 tokens
original MIT
boot
05Skill Claude CodeCodex needs its repo
Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.
not rated 142 2d ago A 23 tokens
original MIT
Skill Claude CodeCodex
Browser inspection and interaction for verifying rendered web UI during development.
not rated 142 2d ago A 16 tokens
original MIT
Skill Claude CodeCodex
Reviews code and plans for logic coherence, correctness, and structural integrity.
not rated 142 2d ago A 19 tokens
original MIT
Skill Claude CodeCodex
Reviews code and plans against the project's coding rules.
not rated 142 2d ago A 14 tokens
original MIT
Skill Claude CodeCodex
Static security review that hunts exploitable vulnerabilities, prioritizing unauthenticated and cross-tenant attack paths.
not rated 142 2d ago A 25 tokens
original MIT
Skill Claude CodeCodex
Deterministic self-evaluation rubric for Coder — scored every run using the GRASP framework.
not rated 142 2d ago A 24 tokens
original MIT
Skill Claude CodeCodex needs its repo
How to maintain .context.md files and docs/FEATURE-MAP.md as the project evolves.
not rated 142 2d ago A 23 tokens
original MIT
Skill Claude CodeCodex
Deterministic self-evaluation rubric for Contextualizer — scored every run using the TRACE framework.
not rated 142 2d ago A 26 tokens
original MIT
dispatch
13Skill Claude CodeCodex
Assembles sub-agent prompts with task brief and routes to the correct provider.
not rated 142 2d ago A 18 tokens
original MIT
grill
14Skill Claude CodeCodex
Protocol that interviews the user in rounds over the Architect's design tree. Three paths control depth. Produces plan.md, arch.md, impl.md.
not rated 142 2d ago A 33 tokens
original MIT
Skill Claude CodeCodex
Structured recovery and escalation when an agent hits a retry loop.
not rated 142 2d ago A 16 tokens
original MIT
Skill Claude CodeCodex
Plan lifecycle — grill entry point, grounding, artifact review, per-epic execution, revision.
not rated 142 2d ago A 23 tokens
original MIT
review-loop
17Skill Claude CodeCodex
Two-mode review loop — single reviewer per epic, three reviewers for full branch.
not rated 142 2d ago A 19 tokens
original MIT
Skill Claude CodeCodex
Adversarial plan review — structural validation and assumption attack on grill artifacts before implementation begins.
not rated 142 2d ago A 26 tokens
original MIT
Skill Claude CodeCodex
Structured review summary format with verdict logic and coverage scoring.
not rated 142 2d ago A 16 tokens
original MIT
Skill Claude CodeCodex
Deterministic self-evaluation rubric for Reviewer — scored every run using the SHIELD framework.
not rated 142 2d ago A 24 tokens
original MIT
Skill Claude CodeCodex
File-based to-do tracking for multi-step and multi-session work.
not rated 142 2d ago A 17 tokens
original MIT
web-search
22Skill Claude CodeCodex
Web search and page fetch through the TinyFish CLI.
not rated 142 2d ago A 14 tokens
original MIT
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: