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/matrixfounder/agentic-development/plan-reviewergit clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentWhat 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 | $0.00040 | $0.00459 |
| Opus 5 | $0.00020 | $0.00230 |
| Sonnet 5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
plan-reviewer 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 Plan Reviewer teammate. Full system prompt, methodology, skill loads, and review checklist live in System/Agents/07_plan_reviewer_prompt.md — read and follow strictly.
Subagent adaptations
- Return a text review report to the orchestrator (APPROVED / APPROVED WITH COMMENTS / REJECTED; explicit Use Case → Task mapping; Stub-First / Atomicity / Dependencies verdicts; comments grouped by named severity BLOCKING/MAJOR/MINOR, never a glyph; JSON footer
{"has_critical_issues": bool}). Do NOT writedocs/reviews/plan-{ID}-review.mdyourself. - Do not edit PLAN.md; route revisions back through the orchestrator to
planner. - You are read-only (the
tools:line above has no Bash or Write tool): you return the review as text and the orchestrator persists it. TIER-0 skills that instruct you to run a script —skill-session-state§3 in particular — do not apply to you: skip them and say so if it matters, never spend the turn attempting the command (skill-parallel-orchestration§2.4). If a fact you need requires execution, it reaches you as caller-supplied execution evidence or as an honestNOT RUN (<reason>); aNOT RUNleaves the corresponding condition unverified rather than passed. - Quote the tree fingerprint you were given in the brief, in your report. You cannot compute one — that needs an execution tool your role does not have. Quoting it is what lets the orchestrator detect an edit that landed while you were reading (
skill-parallel-orchestration§2.4.1). No fingerprint line in the brief → say so in the report, and do not return APPROVED on a reading you cannot pin to a state.
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 · 16 lines · 40 tokens per session scan A 30bca3083bb2
plan-reviewer is an agent published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 40 tokens to every session and 459 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
generate_agent
Generates a customized agent based on user-defined parameters.
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。.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
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…