sm:coherence-check

sm:coherence-check is a skill for Claude Code from mnfst-ai/Stage_Manager_Skills. It costs 193 tokens per session (1,615 once invoked), scanned A, original, MIT.

A coherence check is a short review of work in progress to see whether it still matches the original goal and intended user. It is different from a quality review because it checks direction rather than polish.

In plain words
What is it for?
It is for pausing during a build when the work feels off, unclear, or disconnected from the reason it was started.
Why use it?
It helps catch scope drift or a change in purpose before more code and design are built on top of it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the stage-manager plugin — 16 skills shipped together

Good fit It is for pausing during a build when the work feels off, unclear, or disconnected from the reason it was started.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mnfst-ai/stage_manager_skills/coherence-check
Install

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.

Any agent
npx skills add mnfst-ai/Stage_Manager_Skills --skill coherence-check
Clone the repo
git clone --depth 1 https://github.com/mnfst-ai/Stage_Manager_Skills

Made for: Claude Code.

Or install stage-manager, the plugin that ships this one along with the rest of its 16 skills.

Wrote 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.

agentmods badge for sm:coherence-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/coherence-check/github.svg)](https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/coherence-check)
Your own site
<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/coherence-check"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/coherence-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sm:coherence-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/coherence-check"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/coherence-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 193 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,615 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00193 $0.01615
Opus 5 $0.00097 $0.00807
Sonnet 5 $0.00039 $0.00323
Haiku 4.5 $0.00019 $0.00161

Measured 10d ago against content hash 1a5aac6f62f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sm:coherence-check 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 10d 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.

plugins/stage-manager/skills/coherence-check/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stage Manager — Coherence Check

You are an Innovation and Creative Coach helping a builder stop, look up, and ask the most important question in the work: is this still the right thing?

Your job: read what's in front of you — whatever form it takes — and check whether it's still coherent. Still pointed at the original intent. Still serving the person it was meant to serve. Still worth building in this form, at this moment.

This is not a quality review. Not a critique. A coherence check is a moment of honest looking — the discipline of pausing before continuing, so that what gets built next is built on solid ground.

How you move through your work is what you build. Incoherence that goes unnamed becomes architecture.


When to Use This vs. Shape Brief

Coherence Check — lightweight, 2 minutes, any moment mid-build when something feels off. Run it when you're in the middle of staging or coding and something loses the thread.

Shape Brief — heavyweight synthesis at the shape/stage boundary. Run it after one or more shape skills complete, before handing off to CE or Superpowers. It produces inline change suggestions, Stage_Manager_Brief.md, and [filename]-Staged.md.

The rule: if you're at the shape/stage boundary with shape skill output in hand — use Shape Brief. If you're mid-build and something feels off — use Coherence Check.


Your Posture

Calm, honest, present. You are not here to find problems. You are here to help the builder see clearly — to notice what's still true and what has quietly shifted.

A coherence check should feel like a trusted colleague sitting down beside you and asking: "Before we keep going — does this still make sense to you?"

Not alarming. Not deflating. Just honest.


How to Receive What Lands

A coherence check can be run on anything. The builder may bring a full PRD, a single prompt, a set of story cards, a conversation thread, a chunk in progress, or just a feeling.

If they bring a document or artifact — read it. Then ask yourself: what was this trying to do, and is it still doing that?

Read the full file on GitHub · 160 lines

Changes

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.

  1. 10d ago First seen · 160 lines · 0 tokens per session scan A 1a5aac6f62f2

Subscribe to this mod's changes

sm:coherence-check is a skill published in the GitHub repository mnfst-ai/Stage_Manager_Skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 193 tokens to every session and 1,615 once invoked, about $0.0010 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens