Skill Claude CodeCodex
Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
not rated 17 yesterday A 35 tokens
original MIT
17Stars on the repository
98Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
body-check
02Skill Claude CodeCodex
Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.
not rated 17 yesterday A 30 tokens
original MIT
brief
03Skill Claude CodeCodex
Generate a structured delegation brief for any task.
not rated 17 yesterday A 10 tokens
original MIT
Caddy Audit
04Skill Claude CodeCodex
Quarterly skill that walks the skill-index against the actual SKILL.md files on disk, reports drift (skills indexed that no longer exist, skills on disk that aren't enrolled, skills whose descriptions have changed since enrollment). Hardens the auto-enrollment pipeline against silent rot.
not rated 17 yesterday A 58 tokens
original MIT
caddy-enroll
05Skill Claude CodeCodex
Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll ".
not rated 17 yesterday A 57 tokens
original MIT
Skill Claude CodeCodex
When a [CADDY] hint fires and the principal is confused why, /caddy-explain walks the scoring transparently — which trigger matched, what points it earned, what the threshold was, what other skills were close. Pairs with the legibility thesis. Caddy's decisions should be inspectable on demand.
not rated 17 yesterday A 70 tokens
original MIT
caddy-mute
07Skill Claude CodeCodex
Mute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.
not rated 17 yesterday A 36 tokens
original MIT
Skill Claude CodeCodex
Compact a long capsule chain. Walks parentcapsuleid backward from a head capsule; if chain >= 5, summarizes oldest 3 into a chain-summary capsule. Manual invocation.
not rated 17 yesterday A 42 tokens
original MIT
close
09Skill Claude CodeCodex
Commit the session to durable vault memory and prepare a clean resume point.
not rated 17 yesterday A 15 tokens
original MIT
Skill Claude CodeCodex
Route ONE bounded, mechanical task to the Codex CLI as a non-Claude executor, under the same review-before-merge gate as any other agent-produced diff. Use when the user explicitly asks to hand a task to Codex, or names OpenAI Codex / a non-Claude executor for a mechanical change (rename a symbol across files, add a…
not rated 17 yesterday A 101 tokens
original MIT
Skill Claude CodeCodex
Conservative close-parity updates to GOALSTACK, BELIEFSTATE, SELFMODEL, and PROCEDURES. Writes only explicit or mechanically evidenced deltas; ambiguity means no write.
not rated 17 yesterday A 40 tokens
original MIT
Skill Claude CodeCodex
Echo's comms polling skill. Read an inbox, channel, or message thread and return a structured unread summary — sender, topic, action required, and urgency. Read-only.
not rated 17 yesterday A 42 tokens
original MIT
compact-note
13Skill Claude CodeCodex
Mnemosyne's note compaction skill. Distills a high-churn, bloated vault note into a standing-rule summary + truncated log. Preserves signal, removes noise, explains every preservation decision.
not rated 17 yesterday A 44 tokens
original MIT
Skill Claude CodeCodex
The capsule verb, invoked explicitly — reconcile from the live memory, write a resume-ready capsule, then stop. Mid-session checkpoint or completion capsule; a rolling best-effort version of the same write also runs automatically on every Stop event via daemons/stop-capsule-writer.mjs.
not rated 17 yesterday A 64 tokens
original MIT
Skill Claude CodeCodex
Nightly context trim for ACTIVEPRIORITIES and the dated SESSIONLOG schema. Archives before removal, uses content-hash compare-and-swap, and refuses unknown shapes.
not rated 17 yesterday A 39 tokens
original MIT
Skill Claude CodeCodex
Hypatia's plan critique skill. Takes a strategic plan, architectural decision, or proposal and returns adversarial pre-commitment review — strongest counterargument first, hidden assumptions surfaced, alternatives named.
not rated 17 yesterday A 43 tokens
original MIT
decide
17Skill Claude CodeCodex
Run a decision through the 12-lens framework.
not rated 17 yesterday A 13 tokens
original MIT
deep-recon
18Skill Claude CodeCodex
Run extended multi-agent reconnaissance sessions. Use when asked to brainstorm deeply, explore ideas from multiple angles, or generate a structured recon document.
not rated 17 yesterday A 31 tokens
copy · 100% MIT
Diagnose
19Skill Claude CodeCodex
When something feels off, type /diagnose and describe the symptom. The skill walks the seven-layer stack (kernel, skills, hooks, daemons, vault, doctrine, principal config) and reports which layer is most likely responsible. Caddy pattern applied to debugging.
not rated 17 yesterday A 57 tokens
original MIT
digest
20Skill Claude CodeCodex
Review staged memory candidates from MEMORYCANDIDATES.md. Surface each with promote/skip/supersede options. Does not auto-promote.
not rated 17 yesterday A 32 tokens
original MIT
dream
21Skill Claude CodeCodex
Evidence-gated synthesis over recent operating evidence. Appends admitted lessons and a dated synthesis with propose-only improvement candidates.
not rated 17 yesterday A 25 tokens
original MIT
Envelope
22Skill Claude CodeCodex
Classify any incoming directive as Ship / Ask one focused question / Propose first. Forces a sharp decision instead of a multi-option survey to the principal. The default failure mode for agents is treating ship-work as ask-work (over-surveying) or treating propose-work as ship-work (rushing irreversible changes).…
not rated 17 yesterday A 70 tokens
original MIT
Skill Claude CodeCodex
Hypatia's targeted weakness-finding skill. Given a specific claim, architecture, or decision, finds the single strongest objection and the hidden assumption most likely to be wrong. Sharper and faster than critique-plan.
not rated 17 yesterday A 47 tokens
original MIT
Skill Claude CodeCodex
The exact operational recon sequence for an unfamiliar codebase or unfamiliar area. Replaces "ask the human to clarify" with "read the code first." Most clarification questions are answered by 5 minutes in the relevant file - this skill enforces reading before asking.
not rated 17 yesterday A 57 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: