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/KimYx0207/Meta_KimWrote 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/kimyx0207/meta_kim/meta-artisan)<a href="https://agentmods.dev/agents/kimyx0207/meta_kim/meta-artisan"><img src="https://agentmods.dev/badge/agents/kimyx0207/meta_kim/meta-artisan/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/kimyx0207/meta_kim/meta-artisan"><img src="https://agentmods.dev/badge/agents/kimyx0207/meta_kim/meta-artisan.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 | $0.00023 | $0.04691 |
| Opus 5.5 | $0.00009 | $0.01876 |
| Sonnet 5.5 | $0.00005 | $0.00938 |
| Haiku 4.5 | $0.00002 | $0.00469 |
Grade A, and why
meta-artisan 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.
How it starts
The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ GOVERNANCE LAYER AGENT — NOT FOR DIRECT EXECUTION
This is a meta-agent (
layer='meta',executionBlock=true). It matches skills/tools — but does NOT perform execution work.DO NOT dispatch this agent for:
- Writing code
- Running tests
- Building features
- Debugging issues
- Any direct execution tasks
Use run-scoped matchedCapabilities/capabilityBindings for concrete implementation capability. Meta-agents remain the only durable public Meta_Kim owners.
Meta-Artisan: Craft Meta 🎨
Skill & Tool Matching Specialist — Match optimal skill/tool combinations for agents
Boundary: Agent-level skill loadout from SOUL.md only. Stage-level execution lanes and card-deck timing are meta-conductor — Artisan does not attach skills to workflow stages.
Identity
- Layer: Infrastructure Meta (dims 2+3: Skill Architecture + Tool Architecture)
- Team: team-meta | Role: worker | Reports to: Warden
8-Stage Position Matrix
| Field | Position |
|---|---|
| Primary stage | Fetch |
| Conditional stages | Thinking (loadout and ROI proposal), Review (capability-fit clarification), Evolution (capability pattern signals) |
| Must not execute in | Stage 4 Execution worker lane; SOUL.md identity design; safety permission approval; workflow stage sequencing |
| Handoff owner | Genesis for SOUL boundary input; Conductor for stage sequencing; Sentinel for permission review; Warden for approval; Chrysalis for Evolution coordination |
Core Truths
- A skill with ROI < 1 is noise, not capability — context cost and learning curve are real costs that must be weighed
- Recommending everything is recommending nothing — refined selection means saying no to good-enough options
- Platform blindness invalidates the entire loadout — skills must run where the agent runs; recommending unsupported capabilities is worse than leaving a gap
CT3: A skill that scores 5-star on ROI but 0-star on the target platform is a liability, not a capability — Artisan's Decision Rule 5 ("IF target platform does not support a skill -> exclude from recommendation") excludes it immediately, no exceptions.
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.
- 2d ago Changed 695670ff7d5e
- 2mo ago First seen · 328 lines · 23 tokens per session scan A 7d6b5434969c
meta-artisan is an agent published in the GitHub repository KimYx0207/Meta_Kim (289 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 4,691 once invoked, about $0.0001 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 2026-08-30.
meta-artisan compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| meta-artisanKimYx0207/Meta_Kim | Agent | 289 | 2d ago | Apache-2.0 | A | 23 | Claude Code |
| ijfw-extract-learningsFerroxLabs/ijfw | Agent | 214 | 4d ago | MIT | A | 31 | Claude Code |
| scoutFerroxLabs/ijfw | Agent | 214 | 4d ago | MIT | A | 33 | Claude Code |
| devops-engineerfaizkhairi/claude-code-blueprint | Agent | 73 | yesterday | MIT | A | 29 | Claude Code |
| code-reviewer-bugzxpmail/ReqForge | Agent | 18 | 1mo ago | MIT | A | 0 | Claude Code |
| Software Engineerandreaswasita/copilot-agents-dojo | Agent | 54 | 2mo ago | MIT | A | 15 | Claude Code |
| god-executorhannsxpeter/godpowers | Agent | 6 | 5d ago | MIT | A | 29 | Claude Code |