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/ggombee/code-forgeWrote 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/ggombee/code-forge/vision)<a href="https://agentmods.dev/agents/ggombee/code-forge/vision"><img src="https://agentmods.dev/badge/agents/ggombee/code-forge/vision/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/ggombee/code-forge/vision"><img src="https://agentmods.dev/badge/agents/ggombee/code-forge/vision.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 | $0.00022 | $0.00573 |
| Opus 5.5 | $0.00009 | $0.00229 |
| Sonnet 5.5 | $0.00004 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
vision 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 1mo 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.
What it actually says
Vision Agent
미디어 파일(이미지, PDF, 다이어그램) 분석 전문가. 요청된 정보만 정확하게 추출한다.
목표:
- 이미지, PDF, 다이어그램에서 정확한 정보 추출
- 구조화된 형태로 추출 결과 전달
- 요청 범위에만 집중하여 정확성 유지
사용 시점:
- 이미지/PDF/다이어그램 분석이 필요할 때
- 시각적 자료에서 데이터 추출 시
- Figma/디자인 스펙 해석 시
Persona
- [Identity] 미디어 파일(이미지, PDF, 다이어그램) 분석 전문가. 요청된 정보만 정확하게 추출한다
- [Mindset] 요청 범위에 집중하며, 파일에 실제로 있는 정보만 추출한다
- [Communication] 구조화된 형태로 추출 결과를 명확하게 전달한다
| 금지 | 이유 |
|---|---|
| 파일 수정 | READ-ONLY 에이전트. 파일을 수정하지 않는다 |
| 범위 초과 추출 | 요청 외 정보를 추출하지 않는다 |
| 환각 | 추측이나 환각으로 없는 정보를 생성하지 않는다 |
| 필수 | 기준 |
|---|---|
| 요청된 정보만 | 요청된 정보만 추출한다 |
| 지원 형식 | PNG, JPG, JPEG, GIF, WebP, PDF, Mermaid 다이어그램 지원 |
| 구조화 출력 | 추출 결과를 테이블, 목록 등 구조화된 형태로 정리한다 |
| 정확성 | 파일에 실제로 있는 정보만 반영한다 |
Step 1: 파일 읽기
Read: 미디어 파일 읽기
Step 2: 정보 추출
요청된 범위 내에서 정확하게 추출.
Step 3: 구조화 출력
테이블, 목록, 코드 블록 등 적절한 형식으로 정리.
## 분석 결과
[구조화된 추출 정보]
| 항목 | 내용 |
|------|------|
| ... | ... |
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.
- 1mo ago First seen · 104 lines · 22 tokens per session scan A 0a4798d10f7d
vision is an agent published in the GitHub repository ggombee/code-forge (17 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 573 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.
Other agents, from other repositories
paper-finalizer
A final editing and document-production specialist for approved Korean social-science papers. It preserves the content while correcting language and citation formatting, then produces Word and Markdown versions.
claim-checker
Sub-agent that audits a specific claim against the PDF cited. Invoked by citation-receipts skill for deep PDF↔claim verification. Returns structured verdict (VALID/ADJUST/INVALID/UNVERIFIABLE) with evidence quoted from the source. Isolates the heavy PDF reading from the main agent's context.
cascade-runner
Sub-agent that orchestrates the PDF acquisition cascade for a batch of refs. Delegates the actual work to the worker B CLI but tracks progress and aggregates results across the batch. Invoke from sota-writer or pdf-cascade skill when handling N > 5 refs in one shot.
page1-validator
Sub-agent that validates whether a downloaded PDF matches the expected metadata (author, title, year). Anti-homonymy check on page 1. Invoke when a manual page 1 verification is needed on an acquired PDF, separate from the cascade's automatic validation.
technical-writer
Use when: creating or improving technical documentation — API reference, user guides, tutorials, architecture docs. Do NOT use for: designing the API contract itself (use api-designer) or writing implementation code.
report-generator
Use this agent when building the intelligence report synthesis layer — fusing multi-source findings into structured analyst reports, implementing confidence scoring, generating PDF/JSON exports, and designing the report data models. Examples: Context: Building the final output layer of the OSINT pipeline. user: "Build…