Borrowing it
Nothing to install: this file belongs to generative-computing/mellea-skills-compiler. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/generative-computing/mellea-skills-compiler/main/.claude/commands/mellea-fy-deps.mdgit clone --depth 1 https://github.com/generative-computing/mellea-skills-compilerWrote 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/generative-computing/mellea-skills-compiler/mellea-fy-deps)<a href="https://agentmods.dev/commands/generative-computing/mellea-skills-compiler/mellea-fy-deps"><img src="https://agentmods.dev/badge/commands/generative-computing/mellea-skills-compiler/mellea-fy-deps/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/commands/generative-computing/mellea-skills-compiler/mellea-fy-deps"><img src="https://agentmods.dev/badge/commands/generative-computing/mellea-skills-compiler/mellea-fy-deps.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 | $0.00000 | $0.03908 |
| Opus 5 | $0.00000 | $0.01954 |
| Sonnet 5 | $0.00000 | $0.00782 |
| Haiku 4.5 | $0.00000 | $0.00391 |
Grade A, and why
mellea-fy-deps 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 3d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Melleafy Step 2.5: Dependency Audit and Elicitation
Version: 4.2.0 | Prereq: inventory.json, element_mapping.json | Produces: dependency_plan.json, mellea_api_ref.json, mellea_doc_index.json
Schema: Output
intermediate/dependency_plan.jsonMUST conform to.claude/schemas/dependency_plan.schema.json.
Step 2.5 is entirely deterministic — no LLM invocations. It reads element_mapping.json (where every TOOL_TEMPLATE entry has final_target_file: "pending_step_2.5"), assigns a disposition to every external dependency, elicits user input when the generation mode requires it, commits the plan, and amends element_mapping.json accordingly.
This step must not be skipped. Every external dependency must have an explicit disposition before Step 3 can emit skeletons.
Four sub-steps
2.5a: Dependency audit
Collect every element from inventory.json whose category is C1–C9. For each, look up the default disposition from the table below. Group by category. Also apply any aggregation hints from Step 1b's cross-element pass.
Aggregation during audit: when two elements have aggregation_hint pointing at each other, merge them into one dependency entry with a combined source_elements list and the disposition that covers both.
Output: intermediate/dependency_audit.json — one entry per dependency with entry_id, category, default_disposition, source_elements, and subtype (for C6: http, graphql, mcp, sdk, abstract).
2.5b: Elicitation (ask and config modes only)
If generation mode is auto or config:<path>: skip to 2.5c.
If generation mode is ask: display a terminal UI (using rich) for each dependency in the audit. Show: category, source elements, default disposition, available alternatives. Allow the user to accept the default or override.
If generation mode is config:<path>: read the JSON config file. The config format mirrors dependency_plan.json:plan[] — a list of {entry_id, disposition, override_rationale} objects. Apply overrides to the audit results.
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.
- 3d ago Changed e27d1b23b15d
- 11d ago First seen · 279 lines · 0 tokens per session scan A 89e5e8a490cb
mellea-fy-deps is a command published in the GitHub repository generative-computing/mellea-skills-compiler (49 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,908 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.