Skip to content
Agentmart
Submit a tool

co-health

Use when the Conscientious Objector (or any watchdog) needs a health check on the operator's own cadence — proven live, on demand, never silently.

Skill by Tcuzzo

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying co-health?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tcuzzo-co-health

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when the Conscientious Objector (or any watchdog) needs a health check on the operator's own cadence — proven live, on demand, never silently. CO Health is the autonomic self-healer: tests first, clears failures (auto-revert), then names itself. Self-test battery covers locked-shape integrity, watchdog probe, dual-factor seam, local override path, auto-revert safety net, public release, and skill registry. Bounded — every check has a small fixed budget, never silently retries, never pages the operator on micro-issues. Operator kill switches always work; the Health Doctor never locks out the operator. Trigger words: CO health, co-health, health doctor, autonomic self-healer, watchdog health, watchdog self-test, CO self-test, watchdog alive, watchdog up, is the CO running.

Use cases: testing, finance

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/co-health

What's inside

Skill name
co-health
Description
Use when the Conscientious Objector (or any watchdog) needs a health check on the operator's own cadence — proven live, on demand, never silently. CO Health is the autonomic self-healer: tests first, clears failures (auto-revert), then names itself. Self-test battery covers locked-shape integrity, watchdog probe, dual-factor seam, local override path, auto-revert safety net, public release, and skill registry. Bounded — every check has a small fixed budget, never silently retries, never pages the operator on micro-issues. Operator kill switches always work; the Health Doctor never locks out the operator. Trigger words: CO health, co-health, health doctor, autonomic self-healer, watchdog health, watchdog self-test, CO self-test, watchdog alive, watchdog up, is the CO running.
License
MIT
Instructions
34 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# CO Health — the autonomic watchdog doctor

This is the AIOS-pack load-side surface. The full implementation lives in
the BACKS runtime at `skills/co-health/SKILL.md` and
`backend/services/co_health.py`. The public CLI companion is
`backend/services/co_doctor.py`.

## What the Health Doctor covers

The self-test battery is seven probes, each with a small fixed budget:

1. **Locked shape** — the watchdog's source files hash to the locked value.
2. **Watchdog probe** — the CO actually responds to a probe and returns a
   verdict.
3. **Dual-factor seam** — the TOTP + Telegram path resolves (without firing a
   real challenge).
4. **Local override path** — the four operator kill switches resolve.
5. **Auto-revert safety net** — the snapshot+revert path restores FILE
   CONTENTS (not just hash records).
6. **Public release** — the public CLI is wired and answers `co doctor status`.
7. **Skill registry** — the CO family is registered on the chat surface and
   answerable.

## When to invoke

- On demand — `co doctor status` from any surface that exposes the CLI.
- On cadence — the Health Doctor runs itself on a schedule the operator sets.
- After a watchdog change — the next health check proves the change did not
  break the locked shape.

The Health Doctor is the answer to "is the watchdog actually up?" — proven
live, not narrated.

From Tcuzzo/HydraAgent_public, MIT.

More from Tcuzzo/HydraAgent_public

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Oct 6, 2026 (25 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Tcuzzo

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get co-health running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying co-health?

CallGet help
Cite this page

co-health skill. Agent Mart. https://agentmart.dev/skills/tcuzzo-co-health (last updated 2026-10-24)