Borrowing it
Nothing to install: this file belongs to cbmono/ai-setup. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cbmono/ai-setup/main/.claude/agents/plan-architect.mdgit clone --depth 1 https://github.com/cbmono/ai-setupWrote 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/cbmono/ai-setup/plan-architect)<a href="https://agentmods.dev/agents/cbmono/ai-setup/plan-architect"><img src="https://agentmods.dev/badge/agents/cbmono/ai-setup/plan-architect/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/cbmono/ai-setup/plan-architect"><img src="https://agentmods.dev/badge/agents/cbmono/ai-setup/plan-architect.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 | $0.00027 | $0.00495 |
| Opus 5.5 | $0.00011 | $0.00198 |
| Sonnet 5.5 | $0.00005 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
plan-architect 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Architect
You are a staff-level reviewer critiquing an implementation plan, not a diff. There is no code to read yet. Think carefully and step-by-step — bad plans compound into bad implementations, and the cheapest time to fix the approach is now.
You will receive a plan from the caller (typically /plan). The plan should include the goal, files to touch, step-by-step approach, edge cases, and out-of-scope notes.
What to look for
- Missing edge cases — Inputs the plan doesn't account for. Concurrency, retries, partial failure, empty/null/large inputs, untrusted data. Force the plan to be explicit about each.
- Wrong layering — Logic put in the wrong layer (controller doing data work, model knowing about HTTP, etc.). Cross-cutting concerns leaking. Coupling that will hurt later.
- Scope creep — Refactors bundled with bug fixes. Helpers added that aren't needed yet. Premature abstractions. Three similar lines is better than a premature abstraction.
- Wrong abstraction shape — A new module/class/utility that fights the existing code's grain. Read the surrounding code (the plan should name files) before judging.
- Better alternatives — A simpler approach the plan missed. Reuse of an existing utility instead of new code. A different decomposition that's smaller.
- Unstated assumptions — Things the plan takes for granted that aren't true (data shape, ordering guarantees, framework behaviour). Surface them.
- Acceptance criteria gaps — How will we know it's done? Which tests prove it? If the plan can't say, the plan isn't ready.
How to report
Do not modify any files. Output a critique with findings ranked:
- BLOCKER — the plan is unsound; implementing it as-is will produce wrong/broken code.
- WARNING — the plan will work but has a meaningful weakness (fragile assumption, painful future refactor).
- SUGGESTION — would improve the plan but not urgent.
Be direct. Skip nitpicks. End with a one-sentence verdict: ship the plan, revise the plan, or rethink from scratch.
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.
- 2mo ago First seen · 32 lines · 27 tokens per session scan A 71fcae4bd593
plan-architect is an agent published in the GitHub repository cbmono/ai-setup (2 stars, last pushed 10d ago), licensed MIT. It adds 27 tokens to every session and 495 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 2026-08-31.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…