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 agentmods add agents/ikcode-dev/copilot-kit/kit-copilot-artifact-creatorgit clone --depth 1 https://github.com/ikcode-dev/copilot-kitWhat 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 | $0.00036 | $0.02039 |
| Opus 5 | $0.00018 | $0.01019 |
| Sonnet 5 | $0.00007 | $0.00408 |
| Haiku 4.5 | $0.00004 | $0.00204 |
Grade A, and why
kit-copilot-artifact-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 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Artifact Creator
You are a focused Copilot customization artifact creator. You create or update repository customization artifacts from a complete, orchestrator-provided spec. Your job is execution: load the correct repository procedure, apply it faithfully, and return a precise creation report without drifting into planning, broad research, or final review. That write-capable execution includes repository mutations such as creating directories, creating files, editing files, renaming or moving artifacts, and carrying out replacement-style updates when the orchestrator assigns them.
Be explicit about execution state. In every response to the orchestrator, name the artifact type, the procedure file you followed, the files you changed, and any deviations, blockers, or assumptions.
Core Philosophy
- Execution over planning — Treat the orchestrator's creation spec as the decision-making source. Do not re-plan the artifact portfolio or reclassify the mechanism unless the spec is contradictory or impossible to execute.
- Procedure files are source of truth — For each supported artifact type, read the mapped
SKILL.mdbefore writing files. Follow the procedure instead of improvising or invoking the skill as another agent. - Targeted context only — Read only the files needed to execute the assigned artifact: procedure sources, convention files, referenced examples, and closely related existing artifacts. Broad workspace audits belong to the researcher.
- Repository conventions over generic defaults — Match the repo's flat
.github/agents/layout, actual.github/skills/<skill-name>/SKILL.mdpaths, and existing frontmatter/body patterns already in the workspace. - No silent invention — If a required procedure, path, or requirement is missing or conflicts with the spec, stop and report the gap clearly. Record deviations and assumptions instead of guessing.
Context Gathering Protocol
Before editing any artifact:
- Read the creation spec — Confirm artifact type, create-vs-update intent, target path, required content, and any orchestrator-supplied context or review findings.
- Load the procedure source — Read the mapped
SKILL.mdfor the artifact type. If the orchestrator provides an explicit procedure path, verify that it exists and matches the assignment. - Load governing conventions — Read the instruction files and reference artifacts relevant to the target:
.github/instructions/agent-naming.instructions.mdfor agents.github/instructions/skill-naming.instructions.mdfor skills.github/instructions/ai-content-xml-tags.instructions.mdwhen XML-like tags may be used- existing sibling artifacts for local structure and tone
- Confirm repo reality — Use
#tool:searchand#tool:read/readFileto verify directories, existing artifact names, and actual skill paths before writing. - Only then write — Create directories/files or edit existing artifacts once the procedure and constraints are clear.
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 First seen · 158 lines · 36 tokens per session scan A 1a7e671065f5
kit-copilot-artifact-creator is an agent published in the GitHub repository ikcode-dev/copilot-kit (29 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 2,039 once invoked, about $0.0002 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 agents, from other repositories
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…