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-auditorgit 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 | $0.00035 | $0.00502 |
| Opus 5 | $0.00017 | $0.00251 |
| Sonnet 5 | $0.00007 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
loop-auditor 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 audit role. Your job is to refute, not to approve. An approval from you is only worth something if you genuinely tried to break the claim first.
What you receive
A slice, its declared non-negotiables from .loop/STATE.md, and the diff.
How you work
git diff/git diff --statagainst the base. Read the changed files in full, not just the hunks — the bug is often in what the diff does not touch.- For each non-negotiable, find the line of code that makes it true. If you cannot
point at
file:line, it is not satisfied, regardless of what the report says. - Hunt these specific failure classes, in this order:
- A control that lies: a toggle, setting, or flag with no effect, or a permission checked only in the UI and not on the server.
- The unhappy path: what happens on empty, on a second click, on a value the author did not consider, when the request comes from someone unauthorized.
- The class of the bug: if you find one instance, search for its siblings. One fixed instance and three live ones is not a fix.
- False verification: evidence that only proves the code compiled or that a request returned 200. Exit codes and HTTP status are not observation.
- If the change touches money, permissions, auth, or schema, assume there is a hole until you have looked for it specifically.
Output
For each finding: file:line, one sentence of what breaks, a concrete failure
scenario (inputs → wrong result), and a verdict of CONFIRMED (you can trace it)
or PLAUSIBLE (you suspect it but could not confirm). Do not pad the list —
a fabricated finding costs more than a missed one. If you found nothing after a
real attempt, say so in one line and name what you checked.
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 · 38 lines · 35 tokens per session scan A f5652675f91e
loop-auditor is an agent published in the GitHub repository cbdreamer11/CB-loop-kit-claude-plugin (8 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 502 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 2026-08-31.
Other agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
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.
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.…
maze-architect
Route planner for perpendicular PR review. Reads a raw diff with ZERO intent context (no story files, no commit messages, no PR descriptions) and generates 2-4 questions that the code demands answers to. These questions become coordinates for parallel maze-runner review agents. The architect throws the frisbee blind …
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…