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 supportersimulator/3-surgeons --skill invariance-healthgit clone --depth 1 https://github.com/supportersimulator/3-surgeonsWrote 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/supportersimulator/3-surgeons/invariance-health)<a href="https://agentmods.dev/skills/supportersimulator/3-surgeons/invariance-health"><img src="https://agentmods.dev/badge/skills/supportersimulator/3-surgeons/invariance-health/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/supportersimulator/3-surgeons/invariance-health"><img src="https://agentmods.dev/badge/skills/supportersimulator/3-surgeons/invariance-health.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 | $0.00023 | $0.01522 |
| Opus 5 | $0.00012 | $0.00761 |
| Sonnet 5 | $0.00005 | $0.00304 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
invariance-health 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invariance Health (Metacognition)
Philosophy
The gates evaluate themselves.
A gate system that cannot assess its own effectiveness will either over-gate (delivery freeze) or under-gate (quality erosion). Neither failure mode is acceptable. This skill provides the feedback loop that keeps the invariance suite calibrated.
Auto-Invocation Triggers
| Trigger | When |
|---|---|
| Every 10 gate invocations | Automatic retrospective cycle |
| Aaron asks "how are the gates doing?" | On-demand health check |
| Gate override rate exceeds 30% | Signal that gates may be miscalibrated |
| Delivery velocity drops noticeably | Signal that gates may be over-blocking |
| Bug escapes to production | Signal that gates may be under-blocking |
Metrics Tracked Per Gate Invocation
Log these to the evidence store (~/.3surgeons/evidence.db) for every gate run:
| Metric | What It Measures | Target |
|---|---|---|
| time_to_gate | Total gate duration (seconds) | Light <30s, Standard <120s, Full <300s |
| mode_selected | Light/Standard/Full | Proportional to actual risk |
| sentinel_risk | Sentinel risk level output | Accurate reflection of true risk |
| surgeon_agreement | Did all 3 agree? (yes/partial/no) | Agreement on clear cases, disagreement on ambiguous |
| gate_outcome | pass/fail/bypass | Majority should pass (gates catch design issues, not block everything) |
| override | Did Aaron/Atlas override a finding? | Low rate (<15%) — high override = miscalibrated gate |
| cost_usd | LLM spend for this gate run | Light ~$0, Standard ~$0.003, Full ~$0.01 |
| false_positive | Gate blocked but change was fine (retrospective) | <20% — too many = delivery friction |
| false_negative | Gate passed but change caused issues (retrospective) | <5% — too many = gate not catching enough |
10-Invocation Retrospective
Every 10 gate invocations, run this analysis:
Checklist
You MUST create a TodoWrite task for each step:
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 · 153 lines · 23 tokens per session scan A ae62ebd2bf41
invariance-health is a skill published in the GitHub repository supportersimulator/3-surgeons (2 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 1,522 once invoked, about $0.0001 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
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
image-generation
Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.
deepcode-self-refer
Answers questions about Deep Code CLI itself — including features, configuration options, slash commands, Skills, MCP integration, permissions, notifications, session persistence, and troubleshooting. Use this when users ask how to configure or use Deep Code, how to set up an MCP server, configure notifications (such…
skill-writer
Guide users through creating, updating, debugging, and validating Agent Skills for AI agents. Use when the user wants to create, write, author, design, troubleshoot, validate, or improve a Skill, or needs help with SKILL.md, frontmatter, or skill structure.
image-generator
Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.
video-generator
A video-generation skill that turns text, images, video, or audio references into a video with dialogue and ambient sound.