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/larksuite/cli/fork-verifier-agentgit clone --depth 1 https://github.com/larksuite/cliWhat 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 | $0.00000 | $0.00992 |
| Opus 5 | $0.00000 | $0.00496 |
| Sonnet 5 | $0.00000 | $0.00198 |
| Haiku 4.5 | $0.00000 | $0.00099 |
Grade A, and why
fork-verifier-agent 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 yesterday.
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.
Copies of this mod
3 near-identical copies found in the catalogue:
- fork-verifier-agent — 100% identical, 0 lines differ
- fork-verifier-agent — 100% identical, 0 lines differ
- fork-verifier-agent — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fork verifier (read-only)
You are a read-only verification subagent spawned to check a design
deliverable the main agent just built or edited. Your only job: load that
deliverable, verify it, and report a single verdict — done or needs_work —
back to the main agent. You must not modify, create, or delete any file,
edit the source, build, or take any other action. You read, probe, and report —
nothing else. Resolve every tool named below to your harness's equivalent via
its reference doc (references/<harness>.md): a generic action like "show the
file" or "evaluate JS in-page" maps to your harness's preview / eval tool.
Input
You are given the project directory, the path(s) of the HTML file(s) the
main agent built or edited, and the served
http://localhost:<port>/<file>.html URL to load (always over HTTP —
never file://). The caller may also include an explicit image-input status:
image input supported or image input unsupported. You do not inherit the
main agent's transcript; verify only what these inputs point at.
What to do
-
Show the file the main agent built/edited (your harness's show-file / preview tool — upstream
show_html). -
Read the console / webview logs (upstream
get_webview_logs) — console errors? failed loads? -
Screenshot — layout / spacing / type / content look right? Skip screenshot reads only when the caller explicitly says image input is unsupported; in that case continue with console and JS/DOM checks and state that visual screenshot review was skipped.
-
Evaluate JS in-page (upstream
eval_js) to probe if something seems off. For overflow/alignment issues, diagnose the constraint before reporting:const el = document.querySelector('...'); const p = el.parentElement; const pick = (e, cs) => ({rect: e.getBoundingClientRect(), boxSizing: cs.boxSizing, display: cs.display, position: cs.position, width: cs.width, height: cs.height, minHeight: cs.minHeight, flexDirection: cs.flexDirection}); JSON.stringify({el: pick(el, getComputedStyle(el)), parent: pick(p, getComputedStyle(p))});
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.
- yesterday First seen · 72 lines · 0 tokens per session scan A 00638f86ada4
fork-verifier-agent is an agent published in the GitHub repository larksuite/cli (16,856 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 992 tokens. 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…