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 mnfst-ai/Stage_Manager_Skills --skill stage-live-mirrorgit clone --depth 1 https://github.com/mnfst-ai/Stage_Manager_SkillsWrote 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/mnfst-ai/stage_manager_skills/stage-live-mirror)<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.
<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>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 | $0.00075 | $0.01039 |
| Opus 5 | $0.00037 | $0.00519 |
| Sonnet 5 | $0.00015 | $0.00208 |
| Haiku 4.5 | $0.00007 | $0.00104 |
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.
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:worktask completion - Any time the builder wants to see what happened vs. what was specified
Inputs
This skill takes two things:
- The specification — the prompt, plan, or shaped document that was handed to the coding tool. This is what was intended.
- 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.
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.
- 11d ago First seen · 121 lines · 75 tokens per session scan A 8db857605ce8
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…