Instructions file CodexOpenCode
AGENTS.md instructions for rv198-star/Mindthus, covering agents.md, 默认姿态, no abstract jargon wall, 方法分层纪律 / method layering discipline and skill 地图.
20 11d ago A 3,413 tokens
AGPL-3.0
3l5s
02Skill Claude CodeCodex
Use when a problem is unclear, noisy, repeatedly reworked, or too large to execute directly; also use when a task list looks structured but may not be executable, verifiable, or tied to a falsifiable problem.
20 11d ago A 50 tokens
AGPL-3.0
case-prep
03Skill Claude CodeCodex
Use only when the user explicitly asks to prepare, export, package, or contribute one or all current Mindthus judgment, benchmark, or bounded TPlan cases for analysis.
20 11d ago A 38 tokens
AGPL-3.0
edsp
04Skill Claude CodeCodex
Use when an ambiguous qualitative judgment needs Extreme Deduction and optional Scenario Projection: push variables to extremes, build a structural coordinate system, diagnose malformed propositions, then project concrete scenarios when needed.
20 11d ago A 40 tokens
AGPL-3.0
mpg
05Skill Claude CodeCodex
Use when a plausible mainline or strategic direction meets a concrete carrier/proxy, concentrated scarce-resource exposure, or continue/commit/hold/exit/switch decision under path volatility, costs, delays, fragility, or counter-forces; not for method-reference evidence review.
20 11d ago A 58 tokens
AGPL-3.0
sela
06Skill Claude CodeCodex
Use for long-term system-efficiency versus local-advantage direction pressure, especially old paradigm vs scalable system or external system efficiency vs local/internal advantage; when concrete carrier/exposure/path action is also present, use as a support lens with MPG rather than sole owner.
20 11d ago A 56 tokens
AGPL-3.0
tplan
07Skill Claude CodeCodex
Use when an AI agent needs an OKR-Runtime: a Mission needs script-driven task state, acceptance evidence, decision hooks, human-in-loop authority, or Mission-relative addition, subtraction, selection, closure, and recovery.
20 11d ago A 48 tokens
AGPL-3.0
tvg
08Skill Claude CodeCodex
Use as a value-directed strengthening loop for bounded AI artifacts that need clearer judgment, evidence, trade-offs, handoff, reuse, or action value.
20 11d ago A 33 tokens
AGPL-3.0
Skill Claude CodeCodex
Use when any Mindthus judgment lens may apply; strategic/path/control/framing ambiguity before choosing SELA, MPG, EDSP, WAE, TVG, 3L5S, or tplan. Entry Triage hard-judgment cues;whole-object reduction, forced structural binary, repeated local repair, no-data numeric comparison.
20 11d ago A 72 tokens
AGPL-3.0
wae
10Skill Claude CodeCodex
Use when a workflow, script, schema, agent loop, evidence gate, or review step may be controlling the wrong part of the work; especially when clean structure may be freezing uncertain truth or hiding thin judgment.
20 11d ago A 45 tokens
AGPL-3.0