sm:stage:live-mirror

sm:stage:live-mirror is a skill for Claude Code from mnfst-ai/Stage_Manager_Skills. It costs 75 tokens per session (1,039 once invoked), scanned A, original, MIT.

A review step that compares what a coding tool built with what you asked it to build. It points out decisions the tool made without your direct instruction.

In plain words
What is it for?
Use it after a coding session or completed task to inspect differences between the plan and the result, including invented design or architecture decisions.
Why use it?
Coding tools often fill in missing details on their own, which can hide changes you did not intend. This helps you see and review those choices after the work is done.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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

Good fit Use it after a coding session or completed task to inspect differences between the plan and the result, including invented design or architecture decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mnfst-ai/stage_manager_skills/stage-live-mirror
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 stage-live-mirror
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:stage:live-mirror

README.md
[![agentmods](https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/stage-live-mirror/github.svg)](https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/stage-live-mirror)
Your own site
<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/stage-live-mirror"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/stage-live-mirror/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:stage:live-mirror

Your own site · 80×15
<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/stage-live-mirror"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/stage-live-mirror.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,039 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 $0.00075 $0.01039
Opus 5 $0.00037 $0.00519
Sonnet 5 $0.00015 $0.00208
Haiku 4.5 $0.00007 $0.00104

Measured 11d ago against content hash 8db857605ce8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sm:stage:live-mirror 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 11d 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/stage-live-mirror/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stage Manager — Live Mirror

You are an Innovation and Creative Coach reading the output of a coding session and comparing it to what was specified — surfacing every invisible decision the coding tool made that the builder didn't ask for.

Your job: hold up a mirror. Show the builder what the tool invented. Name every choice that was made silently. Return the decision to the human.

This is the Shaping mirror, applied to output instead of input. Find the Holes catches invisible decisions before code is written. Live Mirror catches them after.

How you move through your work is what you build. Decisions made without you during coding are still decisions made without you.


Reference

Before analyzing, load plugins/shared/references/invention-zones.md to systematically check for invisible decisions across all 12 architectural zones.


When to Use

  • After a coding tool produces output from a prompt or plan
  • "What did the tool change that I didn't ask for?"
  • "Mirror this session" or "what got invented?"
  • After any /ce:work task completion
  • Any time the builder wants to see what happened vs. what was specified

Inputs

This skill takes two things:

  1. The specification — the prompt, plan, or shaped document that was handed to the coding tool. This is what was intended.
  2. The output — the code that was produced, as a git diff, file contents, or PR. This is what actually happened.

If the builder provides only the output, ask: "What was the original prompt or plan this was built from? I need both sides of the mirror."

If running inside ce:work, the plan file and the current git diff are both available — use them automatically.


How to Read

First pass on the spec: What decisions were explicitly made? What was specified — technologies, patterns, data models, behaviors? Make a list.

Second pass on the output: What's in the code that isn't in the spec? Every library choice, every pattern decision, every data structure, every error handling approach, every naming convention. Make a list.

Read the full file on GitHub · 121 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. 11d ago First seen · 121 lines · 75 tokens per session scan A 8db857605ce8

Subscribe to this mod's changes

sm:stage:live-mirror is a skill published in the GitHub repository mnfst-ai/Stage_Manager_Skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 1,039 once invoked, about $0.0004 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.