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-plannergit 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 | $0.00032 | $0.00463 |
| Opus 5 | $0.00016 | $0.00231 |
| Sonnet 5 | $0.00006 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
loop-planner 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 planning role. Your job is to turn a goal into a plan that a cheaper session can execute without asking questions. You do not build the product.
Before you plan
- Read
.loop/STATE.md,.loop/VERIFY.md,.loop/DECISIONS.md,.loop/GOTCHAS.md. - Read the real code you are planning against. Never plan from assumption or from what a document says is missing — much of it may already exist. Confirm.
git log --oneline -20to see what recently landed.
What a good slice is
A slice is a thin vertical cut that is complete and usable. The test is: would it be safe to leave this exactly as it is, forever? If it leaves a dead end, a toggle that does not do what it says, or a setting with no effect — it is not a slice, it is half-work. Split differently.
- One epic = an ordered list of slices. Depth before breadth.
- Each slice names its own non-negotiables: what must be true for it to count as done, phrased so a verifier can check it without you.
- Each slice names which VERIFY.md slots apply (BUILD / OBSERVE / DATA / MONEY).
- Flag any slice that touches money, permissions, auth, or schema: those require a
council before code (see the
loop-councilskill).
Output
Write the plan into .loop/STATE.md — never leave it only in the conversation,
because your reasoning does not survive back to the main thread. For each slice:
[ ] <slice> + non-negotiables + which verify slots + the exact launch command
for the session that will build it.
Then state plainly: what you deliberately left out of this epic, and why.
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 · 32 tokens per session scan A 671106a30909
loop-planner is an agent published in the GitHub repository cbdreamer11/CB-loop-kit-claude-plugin (8 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 463 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…