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.
git clone --depth 1 https://github.com/JavanC/HomunculusWrote 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/commands/javanc/homunculus/hm-goal)<a href="https://agentmods.dev/commands/javanc/homunculus/hm-goal"><img src="https://agentmods.dev/badge/commands/javanc/homunculus/hm-goal.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01710 |
| Opus 5 | $0.00000 | $0.00855 |
| Sonnet 5 | $0.00000 | $0.00342 |
| Haiku 4.5 | $0.00000 | $0.00171 |
Grade A, and why
hm-goal 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 8d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hm-goal — View or Define Your Goal Tree
If architecture.yaml exists, display the current goal tree and ask if changes are needed.
If it doesn't exist, guide the user through creating one.
Always communicate in English regardless of user's global Claude settings.
Behavior
Mode Detection
Check if architecture.yaml exists in the project root.
- Exists → Show Mode
- Doesn't exist → Create Mode
Show Mode (architecture.yaml exists)
Step 1: Read and display
Read architecture.yaml and present the goal tree visually:
🎯 Your Goal Tree
├── code_quality — Ship fewer bugs
│ ├── testing — Every change has tests
│ │ └── realized_by: skills/tdd-workflow.md ✓
│ └── review — Catch issues before merge
│ └── realized_by: # will evolve ○
├── productivity — Move faster
│ └── debugging — Find root causes faster
│ └── realized_by: agents/debugger.md ✓
└── knowledge — Stay current
└── tool_updates — Track useful updates
└── realized_by: # will evolve ○
3 goals / 5 sub-goals
2 implemented (✓) / 3 waiting to evolve (○)
Step 2: Ask
"Want to add, remove, or change any goals?"
- If yes → make the changes, update
architecture.yaml - If no → done
Create Mode (no architecture.yaml)
CRITICAL: Ask ONE question at a time. Wait for the answer before asking the next. Never batch multiple questions in one message.
Step 0: Scan existing project (automatic, no user input needed)
Before asking any questions, silently scan the project to understand what already exists.
What to scan:
| Signal | How to detect |
|---|---|
| Tech stack | package.json, pyproject.toml, Cargo.toml, go.mod, Gemfile, composer.json |
| Test framework | jest.config.*, vitest.config.*, pytest.ini, setup.cfg [tool:pytest], *_test.go, .rspec |
| Test count | Count test files: **/*.test.*, **/*.spec.*, **/test_*.py, **/*_test.go |
| CI/CD | .github/workflows/, .gitlab-ci.yml, Jenkinsfile, .circleci/ |
| Linting | .eslintrc*, .prettierrc*, ruff.toml, .golangci.yml |
| Docs | docs/, README.md, *.mdx in obvious doc directories |
| Existing Claude config | .claude/, CLAUDE.md, .cursorrules, .windsurfrules |
| Top-level structure | ls -1 the project root (directories only) |
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.
- 8d ago First seen · 183 lines · 0 tokens per session scan A 78f690ad266f
hm-goal 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 1,710 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.