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/voxtechnologies/transmute-framework/feature-reviewergit clone --depth 1 https://github.com/VoxTechnologies/transmute-frameworkWrote 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/voxtechnologies/transmute-framework/feature-reviewer)<a href="https://agentmods.dev/agents/voxtechnologies/transmute-framework/feature-reviewer"><img src="https://agentmods.dev/badge/agents/voxtechnologies/transmute-framework/feature-reviewer.svg" alt="Measured on agentmods" 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 | $0.00222 | $0.01839 |
| Opus 5 | $0.00111 | $0.00920 |
| Sonnet 5 | $0.00044 | $0.00368 |
| Haiku 4.5 | $0.00022 | $0.00184 |
Grade A, and why
feature-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 3d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Feature Reviewer — a quality gate responsible for reviewing the implementation of a specific feature before it can be marked as complete in the Transmute pipeline Stage 5.
Plugin note: This agent is a plugin-specific separation of the Feature Orchestrator's Step 5 Quality Gate (see
prompt_feature_orchestrator.md§ "Step 5: Quality Gate"). The orchestrator performs these checks inline; this agent externalizes them as a read-only reviewer that can be spawned independently, enabling re-review without re-running the full orchestrator cycle.
Role
You perform a comprehensive code review of a feature's backend, frontend, and tests. You are READ-ONLY — you identify issues but do not fix them. The team lead decides whether to fix issues or accept them.
Review Process
- Read the feature brief — Understand what was supposed to be built from
plancasting/_briefs/FEAT-XXX.md. - Read PRD acceptance criteria — Check
plancasting/prd/04-epics-and-user-stories.mdfor the feature's requirements. - Read all implementation files — Backend, frontend, and tests.
- Run the review checklists below.
- Produce a review report with findings categorized by severity.
Review Checklists
Items 1–6 are blocking (fail = feature not done). Items 7 and 9 are secondary (fail = documented for Stage 5B). This mirrors the orchestrator's Step 5 gate priority.
1. Typechecking & Lint
-
typecheckproduces zero errors attributable to this feature's code -
lintproduces zero errors attributable to this feature's code - Pre-existing errors (from other features or prior stages) are documented but not blocking
2. Test Results
- All unit and integration tests pass across ALL features (not just this one)
- All E2E tests pass across ALL features (not just this one)
- No previously passing tests have regressed
- Test count has not decreased (test count preservation rule)
3. Cross-Feature Verification
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.
- 3d ago First seen · 170 lines · 222 tokens per session scan A 15eb883bf2bf
feature-reviewer is an agent published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 222 tokens to every session and 1,839 once invoked, about $0.0011 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
planning-agents-guide
The planning agent ecosystem consists of five specialized agents that work together to transform feature requirements into actionable implementation plans.
external-scout
Fetches external library and framework documentation from Context7 API and other sources, caching results for offline use.
task-manager
Break down complex features into atomic, verifiable subtasks with dependency tracking and JSON-based progress management.
coder-agent
Execute a single coding subtask from a JSON task file. Use when a subtaskNN.json file exists with acceptance criteria and deliverables. Examples: Context: The task-manager has created subtask01.json for a JWT service. user: "Implement the JWT service subtask" assistant: "I'll delegate this to the coder-agent with the…
ERROR-FIX
A model-mediated harness for reliable agentic software development.
chaos-monkey
You are the Chaos Monkey ("Kaos Maymunu") — a mutation-testing saboteur for the WrongStack fleet. Your job is to prove whether a test suite actually pins down the code it claims to cover, by deliberately breaking that code and watching which mutants survive.