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-mapgit 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-map)<a href="https://agentmods.dev/skills/generative-computing/mellea-skills-compiler/mellea-fy-map"><img src="https://agentmods.dev/badge/skills/generative-computing/mellea-skills-compiler/mellea-fy-map/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-map"><img src="https://agentmods.dev/badge/skills/generative-computing/mellea-skills-compiler/mellea-fy-map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Prompt Injection · line 23 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00020 | $0.02328 |
| Opus 5 | $0.00010 | $0.01164 |
| Sonnet 5 | $0.00004 | $0.00466 |
| Haiku 4.5 | $0.00002 | $0.00233 |
Grade A, and why
mellea-fy-map 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Melleafy Step 2: Element-to-Primitive Mapping
Version: 4.1.0 | Prereq: inventory.json, classification.json | Produces: element_mapping.json
Schema: Output
intermediate/element_mapping.jsonMUST conform toschemas/element_mapping.schema.json.
Step 2 reads inventory.json and produces element_mapping.json — the routing decision for every element: which file in the generated package, which symbol, which Mellea primitive.
Important: Step 2 does NOT commit dispositions for tool-dependent elements. Every TOOL_TEMPLATE mapping entry is provisional (final_target_file: "pending_step_2.5"). Step 2.5 decides real_impl vs stub vs mock and amends.
Tag-to-primitive table
| Tag | Primary primitive | Target file | Notes |
|---|---|---|---|
EXTRACT |
@generative slot |
slots.py |
Two-step pattern when schema complexity warrants (§below) |
CLASSIFY |
@generative slot |
slots.py |
Return type: -> Literal[...] — Ollama supports constrained decoding |
GENERATE |
m.instruct(format=Schema) |
inline in pipeline.py |
format= always a concrete Pydantic model, never dict |
VALIDATE_OUTPUT |
Requirement |
requirements.py |
Uses validation_fn=simple_validate(...) for structural checks; bare description for semantic checks |
VALIDATE_DOMAIN |
m.instruct(format=DomainSchema) |
inline in pipeline.py |
Checks external artifacts; produces structured verdict, not pass/fail boolean |
TRANSFORM |
m.transform() or m.instruct(format=Schema) |
inline in pipeline.py |
m.transform() when types are known; m.instruct when transformation needs prompted reasoning |
QUERY |
m.query() |
inline in pipeline.py |
Read-only question against data already in scope |
DECIDE |
m.instruct(format=DecisionSchema) |
inline in pipeline.py |
Gates remediation loops (see Remediate below) |
ORCHESTRATE |
Plain Python control flow | pipeline.py |
Not a Mellea primitive — describes flow (sequential phases, branches, loops) |
CONVERSE |
m.chat(), pipeline parameter, or NotImplementedError stub |
varies | Three realisations — see below |
REMEDIATE |
Bounded while loop with m.instruct(format=PatchSchema) |
pipeline.py |
Three mapping entries: modification + evaluation + loop wrapper |
SCHEMA |
Pydantic BaseModel class |
schemas.py |
One class per schema; no nested submodels buried in function defs |
CONFIG |
Final[T] constant |
config.py |
Under # === C<N> ... === section header |
TOOL_TEMPLATE |
Python function | tools.py (provisional) |
Amended by Step 2.5d based on disposition |
DETERMINISTIC |
Plain Python function | pipeline.py or tools.py |
tools.py when shared across branches or >15 lines |
TOOL_INPUT |
Pipeline parameter or loader.py call |
main.py or loader.py |
Data a tool produces that feeds the pipeline |
NO_DECOMPOSE |
No primitive | — | Recorded in element_mapping.json with primitive: "none" for invariant completeness |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 165 lines · 20 tokens per session scan A 7bdaab840fb2
mellea-fy-map is a skill published in the GitHub repository generative-computing/mellea-skills-compiler (48 stars, last pushed 2d ago), licensed Apache-2.0. It adds 20 tokens to every session and 2,328 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…