Skill Claude CodeCodex
Record final outcomes to history.md, not intermediate requests or reversed decisions.
not rated 168 2mo ago A 18 tokens
copy · 100% MIT
168Stars on the repository
47Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
humanizer
26Skill Claude CodeCodex
Tone enforcement patterns for external-facing community responses.
not rated 168 2mo ago A 11 tokens
copy · 100% MIT
init-mode
27Skill Claude CodeCodex
Team initialization flow (Phase 1 proposal + Phase 2 creation).
not rated 168 2mo ago A 17 tokens
copy · 83% MIT
Skill Claude CodeCodex
Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to complete scoped work.
not rated 168 2mo ago A 34 tokens
copy · 100% MIT
Skill Claude CodeCodex
Skill "model-selection" from Azure-Samples/eShopLite, covering model selection, scope, context, 5-layer model resolution hierarchy and agent workflow.
not rated 168 2mo ago A 0 tokens
copy · 95% MIT
nap
30Skill Claude CodeCodex
Reclaims context window budget by compressing agent histories, pruning old logs, archiving stale decisions, and cleaning orphaned inbox files.
not rated 168 2mo ago A 0 tokens
copy · 100% MIT
Skill Claude CodeCodex
Route agent notifications to specific channels by type — prevent alert fatigue from single-channel flooding.
not rated 168 2mo ago A 19 tokens
copy · 100% MIT
Skill Claude CodeCodex
A personal squad is a user-level collection of AI agents that travel with you across projects. Unlike project agents (defined in a project's .squad/ directory), personal agents live in your global config directory and are automatically discovered when you start a squad session.
not rated 168 2mo ago A 0 tokens
copy · 95% MIT
Skill Claude CodeCodex
Teaches agents to reply to PR review comment threads after fixing issues, making resolutions traceable.
not rated 168 2mo ago A 22 tokens
copy · 100% MIT
Skill Claude CodeCodex
Capture Playwright screenshots and embed them in GitHub PR descriptions.
not rated 168 2mo ago A 17 tokens
copy · 100% MIT
Skill Claude CodeCodex
Core conventions and patterns for this codebase.
not rated 168 2mo ago A 12 tokens
copy · 100% MIT
Skill Claude CodeCodex
Confidence: high Domain: work-monitoring Last validated: 2026-03-24.
not rated 168 2mo ago A SkillSpector: pass 0 tokens
original MIT
reflect
37Skill Claude CodeCodex
Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.
not rated 168 2mo ago A 66 tokens
copy · 100% MIT
Skill Claude CodeCodex
Skill "release-process" from Azure-Samples/eShopLite, covering release process, scope, confidence: high, context and rules (non-negotiable).
not rated 168 2mo ago A SkillSpector: warn 0 tokens
original MIT
reskill
39Skill Claude CodeCodex
Team-wide charter and history optimization through skill extraction.
not rated 168 2mo ago A 12 tokens
copy · 100% MIT
Skill Claude CodeCodex
Ensure retrospectives happen on schedule and that their action items are tracked in GitHub Issues — not markdown checklists.
not rated 168 2mo ago A 0 tokens
copy · 100% MIT
Skill Claude CodeCodex
Three-tier agent memory model (hot/cold/wiki) for 20-55% context reduction per spawn.
not rated 168 2mo ago A SkillSpector: warn 25 tokens
original MIT
Skill Claude CodeCodex
Semver versioning rules for Squad SDK and CLI — prevents prerelease version incidents.
not rated 168 2mo ago A 20 tokens
copy · 100% MIT
Skill Claude CodeCodex
Cross-platform path handling and command patterns.
not rated 168 2mo ago A 12 tokens
copy · 100% 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: