mellea-skills-compiler: Command for Claude Code

.claude/commands/mellea-fy-behaviours.md

mellea-fy-behaviours is a command for Claude Code from generative-computing/mellea-skills-compiler. It costs 0 tokens per session (4,285 once invoked), scanned A, original, Apache-2.0.

A reference of known Mellea behaviours and workarounds for version 0.4.2. Mellea is the software library used by the documented pipelines.

In plain words
What is it for?
Use it when generating or validating Mellea pipelines, checking import paths, applying required workarounds, and reviewing the evidence behind each documented behaviour.
Why use it?
It helps generated pipelines avoid library-specific problems and flags checks that may need repeating after upgrades.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is generative-computing/mellea-skills-compiler's own configuration. It tells Claude Code how to work on mellea-skills-compiler itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mellea-skills-compiler configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/generative-computing/mellea-skills-compiler/main/.claude/commands/mellea-fy-behaviours.md
Clone the repo
git clone --depth 1 https://github.com/generative-computing/mellea-skills-compiler

Made for: Claude Code.

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 mellea-fy-behaviours

README.md
[![agentmods](https://agentmods.dev/badge/commands/generative-computing/mellea-skills-compiler/mellea-fy-behaviours/github.svg)](https://agentmods.dev/commands/generative-computing/mellea-skills-compiler/mellea-fy-behaviours)
Your own site
<a href="https://agentmods.dev/commands/generative-computing/mellea-skills-compiler/mellea-fy-behaviours"><img src="https://agentmods.dev/badge/commands/generative-computing/mellea-skills-compiler/mellea-fy-behaviours/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.

agentmods 80×15 button for mellea-fy-behaviours

Your own site · 80×15
<a href="https://agentmods.dev/commands/generative-computing/mellea-skills-compiler/mellea-fy-behaviours"><img src="https://agentmods.dev/badge/commands/generative-computing/mellea-skills-compiler/mellea-fy-behaviours.svg" alt="Reviewed on agentmods" width="80" 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 4,285 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.04285
Opus 5 $0.00000 $0.02142
Sonnet 5 $0.00000 $0.00857
Haiku 4.5 $0.00000 $0.00428

Measured 2d ago against content hash 09c9aca81a17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mellea-fy-behaviours 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 2d 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.

.claude/commands/mellea-fy-behaviours.md · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Melleafy: Known Mellea Behaviours & Workarounds

Version: 4.4.0 | tested against mellea 0.7.x

Generated pipelines MUST include these workarounds. Re-test after upgrading mellea — some may be resolved in future releases. Step 7's known-behaviours lint mechanically checks for KB1, KB2, KB3, KB4, KB6, KB7, KB11. Step 7's session-boundary lint covers KB5. KB9 is advisory only — no lint sub-check.

Version-conditional guidance (0.7 vs pre-0.7 imports, telemetry env vars, OTel attributes) lives in .claude/data/compatibility.yaml and is filtered by installed mellea version at grounding time — not inline here.

Import path grounding: All mellea.* import paths shown in this document were verified against intermediate/mellea_api_ref.json at generation time. If any path raises ModuleNotFoundError after a mellea upgrade, consult mellea_api_ref.json:.modules — it is the authoritative module index for the current installed version. Step 7's import-soundness lint will catch any drifted path in generated packages at validation time.

Citation tiers

Every KB entry ends with a citation marker indicating how the claim was established. When upgrading mellea, re-verify entries marked **Verified**: or **Status**: empirically observed — these have no stable external anchor.

Marker Meaning
**Ref**: <url> Covered by official mellea docs. Verify by reading the linked page.
**Verified**: mellea X.Y.Z source — <file>:<lines> Established by reading mellea source. Version-pinned — re-verify on upgrade.
**Status**: empirically observed Observed at runtime, no doc or source anchor. Treat as fragile.

KB1: m.instruct() returns a ComputedModelOutputThunk, not a Pydantic model

Read the full file on GitHub · 332 lines

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. 2d ago Changed · +3 lines 09c9aca81a17
  2. 10d ago First seen · 329 lines · 0 tokens per session scan A 652a69bb3738

Subscribe to this mod's changes

mellea-fy-behaviours is a command published in the GitHub repository generative-computing/mellea-skills-compiler (49 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,285 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.