wrg32786

68 mods across 2 repositories, 35 stars between them.

critique-plan

25

wrg32786/aigent-os

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.

16 5d ago A 43 tokens MIT

decide

26

wrg32786/aigent-os

Skill Claude CodeCodex

Run a decision through the 12-lens framework.

16 5d ago A 13 tokens MIT

deep-recon

27

wrg32786/aigent-os

Skill 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.

16 5d ago A 31 tokens MIT

associator

28

wrg32786/aigent-os

Agent

You are the Associator in a multi-agent recon session. Your cognitive style is lateral: find non-obvious connections.

16 5d ago A 0 tokens MIT

critic

29

wrg32786/aigent-os

Agent

You are the Critic in a multi-agent recon session. Your cognitive style is adversarial: stress-test ideas through productive antagonism.

16 5d ago A 0 tokens MIT

explorer

30

wrg32786/aigent-os

Agent

You are the Explorer in a multi-agent recon session. Your cognitive style is divergent: cast the widest possible net.

16 5d ago A 0 tokens MIT

synthesizer

31

wrg32786/aigent-os

Agent

You are the Synthesizer in a multi-agent recon session. Your cognitive style is integrative: find the emergent pattern across all inputs.

16 5d ago A 0 tokens MIT

Diagnose

32

wrg32786/aigent-os

Skill 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.

16 5d ago A 57 tokens MIT

digest

33

wrg32786/aigent-os

Skill Claude CodeCodex

Review staged memory candidates from MEMORYCANDIDATES.md. Surface each with promote/skip/supersede options. Does not auto-promote.

16 5d ago A 32 tokens MIT

dream

34

wrg32786/aigent-os

Skill Claude CodeCodex

Evidence-gated synthesis over recent operating evidence. Appends admitted lessons and a dated synthesis with propose-only improvement candidates.

16 5d ago A 25 tokens MIT

Envelope

35

wrg32786/aigent-os

Skill 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).…

16 5d ago A 70 tokens MIT

find-weakness

36

wrg32786/aigent-os

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.

16 5d ago A 47 tokens MIT

First 10 Moves

37

wrg32786/aigent-os

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.

16 5d ago A 57 tokens MIT

first-win

38

wrg32786/aigent-os

Skill Claude CodeCodex

The day-one first-win menu. Three dead-simple, high-value tasks (two zero-dependency) that each put a real, usable artifact in the operator's hands in minutes, so the "ship something real" promise is met on day one and never waits on a connector or OAuth.

16 5d ago A 61 tokens MIT

frontend-slides

39

wrg32786/aigent-os

Plugin Claude Code

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files.

16 5d ago A tokens not measured MIT

frontend-slides

40

wrg32786/aigent-os

Skill Claude CodeCodex

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

16 5d ago A 63 tokens MIT

Honesty Check

41

wrg32786/aigent-os

Skill Claude CodeCodex

Run the volunteering ledger before declaring work done. Forces surfacing of what changed/didn't, what was noticed-but-not-fixed, what was guessed, and what tradeoffs were made on the principal's behalf. The standard - the principal should never be surprised later by something the agent knew at the time.

16 5d ago A 65 tokens MIT

humanize-docs

42

wrg32786/aigent-os

Skill Claude CodeCodex

Transform AI-generated documentation into human-readable prose with personality. USE WHEN: Converting rigid AI docs (checklist spam, CAPS LOCK emphasis, perfect symmetric structures, template dumps) into flowing, conversational writing that feels colleague-authored. Different from /humanizer — that skill detects AI…

16 5d ago A 125 tokens MIT

impeccable

43

wrg32786/aigent-os

Skill Claude CodeCodex

Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for…

16 5d ago A 90 tokens MIT

learn-from-failure

44

wrg32786/aigent-os

Skill Claude CodeCodex

When a failure occurs, classify it, check for repetition, and produce a durable artifact that prevents recurrence.

16 5d ago A 0 tokens MIT

Learn

45

wrg32786/aigent-os

Skill Claude CodeCodex

When the principal is in learning mode (reading a repo, watching a talk, processing a new tool), /learn takes a brief input and produces a structured note in vault/concepts/learning/ with category, modern-stack location, relevance verdict, and reconsideration triggers. Captures the value of every learning sweep…

16 5d ago A 73 tokens MIT

meta-improve-vault

46

wrg32786/aigent-os

Skill Claude CodeCodex

Unique project-local route to the canonical constrained self-improvement protocol. Accepts only operator-approved Dream candidates.

16 5d ago A 27 tokens MIT

meta-improve

47

wrg32786/aigent-os

Skill Claude CodeCodex

Canonical constrained self-improvement protocol. Reads operator-approved Dream candidates and never self-merges or self-approves.

16 5d ago A 27 tokens MIT

wrg32786/aigent-os

Skill Claude CodeCodex

Unique project-local fire verb for the seven-leg nightly close-parity pass. Proves and loads the canonical top-level skill.

16 5d ago A 31 tokens MIT