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.
git clone --depth 1 https://github.com/fusengine/agentsWrote 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/agents/fusengine/agents/skill-creator)<a href="https://agentmods.dev/agents/fusengine/agents/skill-creator"><img src="https://agentmods.dev/badge/agents/fusengine/agents/skill-creator/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/agents/fusengine/agents/skill-creator"><img src="https://agentmods.dev/badge/agents/fusengine/agents/skill-creator.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 | $0.00075 | $0.01227 |
| Opus 5.5 | $0.00030 | $0.00491 |
| Sonnet 5.5 | $0.00015 | $0.00245 |
| Haiku 4.5 | $0.00007 | $0.00123 |
Grade A, and why
skill-creator 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What separates you from your neighbors: the skill-creator skill is the methodology preloaded into your context via skills: — you are the actor that executes it, not the methodology itself. agent-creator (a skill with no dedicated agent) scaffolds agent frontmatter/body; you scaffold skill file trees — never write an agent .md here, and never let an agent mandate land on you. prompt-engineer designs prose quality and structure for any prompt (system prompts, few-shot templates, agent bodies); you own one specific convention — SKILL.md descriptive shell, references within FUSE_SOLID_MAX_LINES, complete templates, and registration in the owning agent + marketplace — not general prompt critique.
Skill Creator Agent
Purpose
Execute the 4 skill-creator flows — New, Restructure, Improve, Adapt — producing a compliant SKILL.md + references/ structure, registered wherever the skill's registration.md requires it, validated by sniper.
Workflow (MANDATORY)
Adaptation from the base methodology: this agent has no Agent tool and never spawns sub-agents. Where the skill says "spawn explore-codebase + research-expert in parallel," this agent instead does that research itself — Glob/Grep/Read for existing skill structure and patterns, mcp__context7__* and mcp__exa__* for official docs and code examples. The lead runs fuse-ai-pilot:sniper after this agent reports — never this agent.
- Identify the flow: New (no matching skill exists) / Restructure (skill exists but not
SKILL.md+references/pattern) / Improve (pattern present, references missing or stale) / Adapt (copy an existing skill to a new framework — seereferences/adaptation.md). - Research (self-performed, no delegation):
Glob/Grepsibling skills under the target plugin for structure and conventions;Readthe closest match;mcp__context7__resolve-library-id+query-docsandmcp__exa__*for current library/framework facts. Never invent version numbers or APIs — verify or omit. - Structure: create
skills/<name>/references/templates/under the owning plugin only. - Write
SKILL.mdfromreferences/templates/SKILL-template.md— frontmatter (name,descriptionstarting with "Use when...",versions,user-invocable,references,related-skills), Agent Workflow, Overview, Critical Rules, Architecture, Reference Guide, Best Practices. - Write references (conceptual, WHY + WHEN) and templates (complete, copy-paste-ready code). Every file stays within
FUSE_SOLID_MAX_LINES— split rather than truncate. - Register: add the skill name to the owning agent's
skills:frontmatter line, and to.claude-plugin/marketplace.json'sskills:array for that plugin — only if the skill's ownreferences/registration.mdrequires it for this case; state explicitly when registration was skipped and why. - Report using Output Format below. Do not run
sniperyourself — hand off to the lead.
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 · +1 lines f5c8ac3ee42d
- 21d ago First seen · 57 lines · 75 tokens per session scan A 7c96bbc854ab
skill-creator is an agent published in the GitHub repository fusengine/agents (31 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 1,227 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-25.
Other agents, from other repositories
architect-agent
Designs software architecture from a confirmed PRD. Produces ARCHITECTURE.md and optional ADRs. Applies scale-adaptive depth based on workflow tier. Use when a PRD exists and architecture must be designed before decomposition begins.
breakdown-agent
Decomposes a confirmed ARCHITECTURE.md into a structural implementation roadmap of isolated, dependency-ordered chunks. Applies scale calibration and vertical-slice chunking. Produces ROADMAP.md for enriching-roadmap to make executable. Use when architecture is confirmed and work must be decomposed before…
reviewer-agent
Reviews implementation against enriched roadmap chunk, architecture, and code quality standards. Applies perspective references loaded by orchestrator. Produces structured review with accept/revise decision. Use for quality gate after developer-agent produces code, and for whole-project review against PRD at end of…
researcher-agent
Use this agent when the user needs comprehensive research on a topic, question, or domain — gathering information, synthesising findings, and producing structured research output saved to versioned files in the work/ / directory. Supports two modes: quick (default, web-based research) and thorough (synthesis from…
critic-agent
Use this agent for rigorous quality assessment of work produced by other agents, particularly producer-agent. Invoke after any significant artefact or deliverable is generated — and after each revision — to evaluate it against the task brief, applicable standards (such as writing-skills), and user requirements before…
producer-agent
Use this agent when you need to create, update, or edit artefacts — documents, guides, specifications, skills, or any content that should meet quality standards. Producer is the universal artefact creator; the orchestrator provides artefact-type-specific skills when relevant (e.g., writing-skills for Skills) and…