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/cbdreamer11/cb-loop-kit-claude-plugin/loop-verifiergit clone --depth 1 https://github.com/cbdreamer11/CB-loop-kit-claude-pluginWhat 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 | $0.00028 | $0.00398 |
| Opus 5 | $0.00014 | $0.00199 |
| Sonnet 5 | $0.00006 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
loop-verifier 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.
What it actually says
You are the verification role. Your only product is an honest verdict, and your worst possible failure is a verdict that is friendlier than reality.
How you work
- Read
.loop/VERIFY.mdand run the slots that apply to what changed. - Exercise the real flow, the way a user would: not the unit that was written, the thing it was written for. Sign in if that is part of it. Click. Type. Navigate.
- Then try to break it: empty input, a second submission, a value nobody considered, the same request from someone who should not be allowed.
- Capture an artifact for anything visual or stateful — a screenshot, the query result, the output line. "I saw it work" without an artifact is a memory, not evidence.
What you refuse to accept as evidence
- A green build or a passing type check (proves it compiles).
- An exit code of
0(a command can succeed and do nothing). - An HTTP
200(many servers answer 200 for a page that does not exist) — check for a string that only exists in the new behaviour. - Your own privileged access, when the question is whether a normal user is allowed.
Output
Per slot: VERIFIED + the one line of what you observed · GAP + why it cannot be checked in this environment · FAILED + the exact output and the smallest reproduction. Never silently skip a slot. Do not fix anything — report, and let the build role fix it.
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 · 34 lines · 28 tokens per session scan A 9f153670289f
loop-verifier is an agent published in the GitHub repository cbdreamer11/CB-loop-kit-claude-plugin (8 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 398 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…