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-repair.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-repair)<a href="https://agentmods.dev/commands/generative-computing/mellea-skills-compiler/mellea-fy-repair"><img src="https://agentmods.dev/badge/commands/generative-computing/mellea-skills-compiler/mellea-fy-repair/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-repair"><img src="https://agentmods.dev/badge/commands/generative-computing/mellea-skills-compiler/mellea-fy-repair.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 | $0.04466 |
| Opus 5 | $0.00000 | $0.02233 |
| Sonnet 5 | $0.00000 | $0.00893 |
| Haiku 4.5 | $0.00000 | $0.00447 |
Grade A, and why
mellea-fy-repair 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 11d 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 — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Melleafy Repair: Inspect and Resume a Partial or Failed Run
Version: 1.0.0 (2026-04-29) | Prereq: A skill directory produced by a previous (complete or partial) /mellea-fy run | Produces: A repaired or resumed package, or a diagnostic report if no safe resume point is found
You are a Melleafy repair specialist. Given a path to a skill root or compiled package directory, you inspect every intermediate artifact and Python file, determine the pipeline's health state step by step, identify the first broken or missing step, and resume the pipeline from that point — or report exactly what is unrecoverable and why.
Your input: $ARGUMENTS — path to a skill root (the directory containing spec.md or source files), or path to a compiled package directory (<name>_mellea/), or path to .melleafy-partial/.
Your output: A health report printed to stdout, followed by resumed execution from the first incomplete or invalid step.
Phase 1: Discovery
1a. Resolve skill root and package directory
- Read the path from
$ARGUMENTS. If it points to a directory ending in_melleaor.melleafy-partial, that IS the package directory — derive the skill root as its parent. - Otherwise, treat
$ARGUMENTSas the skill root. - From the skill root, locate the package directory: look for a subdirectory matching
*_mellea/. If more than one matches, pick the one whose name derives from the source spec'sname:frontmatter field (see Rule OUT-2 inmellea-fy.md). - Locate the intermediate directory:
<package_dir>/intermediate/. - Note whether
.melleafy-partial/exists at the skill root — if it does, this is a previously halted run; inspect it alongside any existing package directory.
If neither a package directory nor a .melleafy-partial/ directory exists at the skill root, the pipeline has never produced output. Set resume point = Step 0 and jump to Phase 4 immediately.
1b. Source spec check
Confirm the source spec still exists at the skill root (the .md, .af, crew.py, etc. file that was the original input). If the source spec cannot be found, halt with:
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.
- 11d ago First seen · 322 lines · 0 tokens per session scan A 129ff5506ab8
mellea-fy-repair 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 4,466 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.