agentmods.dev

health

health is a command for coding agents from primeline-ai/evolving-lite. It costs 24 tokens per session (503 once invoked), scanned A, original, MIT.

A command that runs the Self-Star Doctor, which checks seven parts of a self-improvement loop and reports each one as green, yellow, or red.

In plain words
What is it for?
It is for checking delegation, fitness scoring, automatic evolution, maintenance, verification, security, and the Kairn connection.
Why use it?
It shows whether the loop is working and identifies degraded or missing parts that need attention.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the evolving-lite plugin — 2 skills, 16 commands, 6 agents, 6 hooks shipped together

not rated 48 19d ago A scan 24 tokens original MIT
View the source file primeline-ai/evolving-lite primeline.cc
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.

agentmods
npx agentmods add commands/primeline-ai/evolving-lite/health
Clone the repo
git clone --depth 1 https://github.com/primeline-ai/evolving-lite

Or install evolving-lite, the plugin that ships this one along with the rest of its 2 skills, 16 commands, 6 agents, 6 hooks.

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 health

README.md
[![agentmods](https://agentmods.dev/badge/commands/primeline-ai/evolving-lite/health.svg)](https://agentmods.dev/commands/primeline-ai/evolving-lite/health)
Your own site
<a href="https://agentmods.dev/commands/primeline-ai/evolving-lite/health"><img src="https://agentmods.dev/badge/commands/primeline-ai/evolving-lite/health.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 503 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00024 $0.00503
Opus 5 $0.00012 $0.00251
Sonnet 5 $0.00005 $0.00101
Haiku 4.5 $0.00002 $0.00050

Measured 5d ago against content hash d5f9e18ec6f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 5d 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.

commands/health.md · 35 lines

What it actually says

Run the native Self-Star Doctor and show the user the junction board.

Process

  1. Run the Doctor:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/doctor.py"

  1. Show the user the board it prints. It covers 7 junctions:

    • delegation - synthetic prompt produces a valid delegation decision row
    • fitness - a synthetic event flows to a bounded cognitive-fitness score
    • autoevolve - the optimizer is present, kill-switches read correctly, one scored mutation cycle runs
    • steward - the maintenance checks emit zero false findings on a clean repo
    • verifier-spine - the EPT spine resolves and a markerless completion claim is blocked under autonomy
    • security - the tier-check classifies a known command and the content-scanner flags a planted secret + injection
    • kairn-link - the user's Kairn prerequisite is installed and reachable

  2. Interpret for the user:

    • GREEN = healthy and proven by a synthetic pulse.
    • YELLOW = present but degraded (e.g. Kairn installed but its MCP server not yet registered). Tell them the one concrete step the detail field names.
    • RED = absent or throwing. The most common RED is kairn-link on a fresh machine: tell them to run pip install kairn-ai (Kairn is a required prerequisite) and register its MCP server in their Claude Code config.

Notes

  • The Doctor runs its synthetic loop pulse in an isolated scratch copy of the plugin. It never writes your real ledgers, so running /health as often as you like is safe.
  • The Doctor heals conservatively: it creates only missing empty scaffolding (cache dirs, ledgers, .gitkeep). It will ask before touching your settings.json and never overwrites or deletes anything.
  • For machine-readable output: python3 "${CLAUDE_PLUGIN_ROOT}/scripts/doctor.py" --json.
  • The same Doctor runs once automatically on your first session (a quick wiring + preflight check); /health is the full, re-runnable version.
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. 5d ago First seen · 35 lines · 24 tokens per session scan A d5f9e18ec6f4

Subscribe to this mod's changes

health is a command published in the GitHub repository primeline-ai/evolving-lite (48 stars, last pushed 19d ago), licensed MIT. It adds 24 tokens to every session and 503 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 2026-08-30.

Building agentsDebuggingai-codingclaude-codeclaude-code-plugincontext-managementdelegationdeveloper-tools
Related

Other commands, from other repositories

my_brand

Interactive brand identity creation with archetypes, colors, typography, and voice guidelines. Use when user mentions "brand", "colors", "typography", "brand.md", "design system", or "visual identity".

anilcancakir/claude-code-plugins · 46 tokens

my_commit

Create a well-formatted commit following project conventions (auto-detects Conventional Commits, Gitmoji, or Simple style).

anilcancakir/claude-code-plugins · 29 tokens

my_send

Complete pre-commit workflow - runs review, docs, and commit in sequence.

anilcancakir/claude-code-plugins · 18 tokens

my_audit

Audit existing Claude Code setup and project documentation with quality report. Use when user mentions "audit", "check setup", "quality report", "review CLAUDE.md", or "what's missing".

anilcancakir/claude-code-plugins · 44 tokens

my_setup

Create optimized CLAUDE.md using project.md, brand.md, and codebase analysis. Use when user mentions "setup", "CLAUDE.md", "configure Claude", "claude code setup", or "technical docs".

anilcancakir/claude-code-plugins · 49 tokens

my_research

Start comprehensive business research with market analysis, competitor intelligence, and idea validation.

anilcancakir/claude-code-plugins · 18 tokens