Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MiaoDX/intuitive-flow --skill intuitive-reduce-entropygit clone --depth 1 https://github.com/MiaoDX/intuitive-flowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/miaodx/intuitive-flow/intuitive-reduce-entropy)<a href="https://agentmods.dev/skills/miaodx/intuitive-flow/intuitive-reduce-entropy"><img src="https://agentmods.dev/badge/skills/miaodx/intuitive-flow/intuitive-reduce-entropy.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.01023 |
| Opus 5 | $0.00032 | $0.00511 |
| Sonnet 5 | $0.00013 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
intuitive-reduce-entropy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intuitive Reduce Entropy
Use this skill to find a bounded set of changes that remove real maintainer or execution friction. Prefer deletion, reuse, and one canonical owner over new workflow, code, test, or documentation surfaces.
Modes
| Mode | Use when | Output | Redirect when |
|---|---|---|---|
| Repo entropy | The repo feels messy, stale, hard to navigate, or has no known cleanup owner. | Ranked maintenance candidates and specialist owners. | A concrete seam is already selected; use its specialist or $intuitive-refactor. |
| Plan entropy | An idea, draft plan, or preflight needs missing decisions, weak assumptions, scope leaks, or proof gaps found. | Ranked plan risks and the next planning owner. | The contract is already approved; use $intuitive-flow. |
| Discovery loop | The user asks to continue until meaningful cleanup saturates. | Fresh bounded rounds with deduplicated clear, parked, and rejected items. | A selected queue is ready for $intuitive-refactor. |
Before auditing, state:
Selected mode:
Why:
Redirect:
Discovery intensity: <quick scan | selection scan | saturation scan>
Read First
Load only the reference needed for the active pass:
| Need | Read |
|---|---|
| Mode selection, discovery-loop behavior, plan-ledger boundaries | references/discovery-modes.md |
| High-noise summaries, materiality gate, no-change threshold | references/high-noise-and-materiality.md |
| Ranking, architecture review, delegation, specialist routing | references/ranking-and-routing.md |
| Candidate packet, user decision gates, handoff and final shapes | references/handoff-and-reporting.md |
| Reference index | references/detailed-guidance.md |
For broad repo scans, read the repo's thin orientation surface and run the bundled high-noise summary before searching planning archives, logs, generated trees, or other high-noise roots. Deep-read only enough to prove a candidate.
Candidate Gate
Every selected candidate must pass both gates:
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/detailed-guidance.md 871 B
- references/discovery-modes.md 16 KB
- references/handoff-and-reporting.md 6.8 KB
- references/high-noise-and-materiality.md 12 KB
- references/ranking-and-routing.md 16 KB
- scripts/bounded-command-summary.mjs 6.6 KB runs code
- scripts/high-noise-summary.mjs 6.7 KB runs code
- scripts/high-noise-summary.test.ts 6.0 KB runs code
- scripts/materiality-gate.mjs 9.2 KB runs code
- scripts/materiality-gate.test.ts 7.0 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed · +2 lines a1fb4c6c4192
- 7d ago First seen · 110 lines · 63 tokens per session scan A 100ab7bf41cb
intuitive-reduce-entropy is a skill published in the GitHub repository MiaoDX/intuitive-flow (48 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 1,023 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
spawn-agent
Spawn worker agents (Gemini CLI or Codex CLI) to keep main context clean. Use for implementation, codebase research, context gathering, or any scoped work that would pollute the orchestrator's context.
dev-updates
Detect and summarize uncommitted git changes grouped by feature area, then generate a structured commit message. Use when the user says "what's the update?", "what changed?", "summarize my changes", "what have I done?", or "what did I update?".
codeck
Route explicit requests from a host coding agent to one or more locally configured AI executors through Codeck, attach Markdown or other project files, moderate cross-model consultation, expose disagreements, and synthesize traceable results. Use when the user explicitly names Codeck or asks to consult, compare, or…
turnbreak
Shows you something worth reading while your coding agent works, then notifies you when it's done. Use this skill to install turnbreak's turn-start/turn-stop hooks for Claude Code, Codex, Gemini CLI, or Copilot CLI, or to manage its interests and settings.
tink
Self-growing harnesses for Claude Code. Use to cast, verify, frog, and weave task harnesses.
code-review
Perform thorough code review and audit of implemented features. Compares implementation against the technical plan, checks for AI-specific risks, and provides actionable feedback. Activate for: review, audit, code quality assessment, security review.