A command that displays the current state of the Homunculus evolution system, including its goals, instincts, skills, agents, evaluations, observations, experiments, and reports.

Use it to check evolution goals, count active and archived instincts, review skill versions and evaluation results, inspect observations and experiments, and see recent reports.

It collects the system's progress indicators in one compact dashboard instead of requiring you to inspect multiple files and folders.

hm-status — Command for coding agents by JavanC: A command that displays the current state of the…

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/javanc/homunculus/hm-status

Clone the repo

git clone --depth 1 https://github.com/JavanC/Homunculus

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/javanc/homunculus/hm-status.svg)](https://agentmods.dev/commands/javanc/homunculus/hm-status)

Your own site

<a href="https://agentmods.dev/commands/javanc/homunculus/hm-status"><img src="https://agentmods.dev/badge/commands/javanc/homunculus/hm-status.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 429 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00429
Opus 5	$0.00000	$0.00215
Sonnet 5	$0.00000	$0.00086
Haiku 4.5	$0.00000	$0.00043

Measured 5d ago against content hash f5b4b7b62457, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

hm-status 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/hm-status.md · 50 lines

What it actually says

/hm-status — Evolution Status Dashboard

Show the current state of the Homunculus evolution system.

Always communicate in English regardless of user's global Claude settings.

Behavior

Gather and display all evolution metrics in a compact dashboard.

Data to Collect

Goal Tree: Read architecture.yaml, count goals and sub-goals
Instincts: Count files in homunculus/instincts/personal/ and archived/
Skills: Count files in homunculus/evolved/skills/, note versions
Agents: Count files in homunculus/evolved/agents/
Eval Specs: Count files in homunculus/evolved/evals/
Observations: Count lines in homunculus/observations.jsonl
Experiments: Count files in homunculus/experiments/
Reports: List recent reports in homunculus/reports/

Output Format

🧬 Homunculus Status
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Goal Tree:     5 goals / 12 sub-goals
Instincts:     24 active / 8 archived
Skills:        3 evolved (all 100% eval)
Agents:        1 specialized
Observations:  1,247 recorded
Experiments:   2 completed / 1 queued

Recent Skills:
  ✓ tdd-workflow v1.2 — 100% (11 scenarios)
  ✓ debugging-patterns v1.1 — 100% (8 scenarios)
  ✓ shell-automation v1.0 — 100% (6 scenarios)

Last Evolution: 2026-03-22
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Important

Use actual file counts, not hardcoded numbers
Keep output compact — one screen max
If the system is fresh, show zeros and next steps
Don't run any evaluations — just report current state

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.

5d ago First seen · 50 lines · 0 tokens per session scan A f5b4b7b62457

Subscribe to this mod's changes

hm-status is a command published in the GitHub repository JavanC/Homunculus (15 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 429 tokens. 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.

hm-status

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/hm-status — Evolution Status Dashboard

Behavior

Data to Collect

Output Format

Important

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement