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.
npx skills add generative-computing/mellea-skills-compiler --skill mellea-fy-validategit 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/skills/generative-computing/mellea-skills-compiler/mellea-fy-validate)<a href="https://agentmods.dev/skills/generative-computing/mellea-skills-compiler/mellea-fy-validate"><img src="https://agentmods.dev/badge/skills/generative-computing/mellea-skills-compiler/mellea-fy-validate/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/skills/generative-computing/mellea-skills-compiler/mellea-fy-validate"><img src="https://agentmods.dev/badge/skills/generative-computing/mellea-skills-compiler/mellea-fy-validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 226 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00018 | $0.05250 |
| Opus 5 | $0.00009 | $0.02625 |
| Sonnet 5 | $0.00004 | $0.01050 |
| Haiku 4.5 | $0.00002 | $0.00525 |
Grade A, and why
mellea-fy-validate 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 9d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Melleafy Step 7: Static Validation
Version: 4.3.1 (2026-04-28) | Prereq: Steps 3–6 complete | Produces: intermediate/step_7_report.json
Step 7 is the workflow's final gate. Seventeen lints in three tiers. No LLM invocations. No mutation of the generated package. Outcome is binary overall — pass or halt.
Run as: melleafy lint <package_path> (standalone), or automatically at the end of melleafy run.
Three-tier architecture
Tier 1 — Parseability (halt immediately on failure)
parseable: every .py file in the generated package passes ast.parse() without error. Then, the package entry module (<package_name>.pipeline) must import cleanly via importlib.import_module() in a subprocess. This catches wrong external import paths (e.g. mellea.stdlib.strategies vs the real mellea.stdlib.sampling) that ast.parse() cannot detect.
Implementation:
-
Parse all .py files in parallel: For every
.pyfile in<package_name>/, attemptast.parse()concurrently. Collect ALL parse errors across all files before halting (do not fail on the first error). This gives the repair loop the complete error list for all failing files in one run, reducing repair iterations. -
Then, import check: run
python -c "import <package_name>.pipeline"as a subprocess from the package's parent directory. AModuleNotFoundErrororImportErroris a lint failure, not a missing-dependency advisory.
If this lint fails, Step 7 halts. Tier 2 and Tier 3 don't run. The failure report contains all collected syntax errors and import errors (nothing else is meaningful before parsing).
Tier 2 — Structural lints (collect all, halt before Tier 3)
Run all 13 lints in parallel. Each lint is independent and can be executed concurrently. Dispatch all 13 lint operations simultaneously in a single turn (not sequentially, one per turn). All tier-2 lints run to completion even if one fails; results are collected then the tier verdict is determined.
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.
- 9d ago First seen · 227 lines · 18 tokens per session scan A 476214d3d2e6
mellea-fy-validate is a skill published in the GitHub repository generative-computing/mellea-skills-compiler (48 stars, last pushed yesterday), licensed Apache-2.0. It adds 18 tokens to every session and 5,250 once invoked, about $0.0001 per session on Opus 5. 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.