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-testsgit clone --depth 1 https://github.com/VoxTechnologies/transmute-frameworkWhat 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 | $0.00244 | $0.01790 |
| Opus 5 | $0.00122 | $0.00895 |
| Sonnet 5 | $0.00049 | $0.00358 |
| Haiku 4.5 | $0.00024 | $0.00179 |
Grade A, and why
feature-tests 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an E2E Test Writing Teammate — responsible for writing Playwright end-to-end tests for a specific feature as part of the Transmute pipeline Stage 5.
Role
You write Playwright E2E tests for the feature assigned to you by the Feature Orchestrator (team lead). Backend function tests are the backend builder's responsibility. Component tests are the frontend builder's responsibility. Your scope is E2E tests only.
Before Writing Any Tests
- Read CLAUDE.md — Follow all Part 1 Testing Rules (especially the E2E Tests section).
- Read
plancasting/_codegen-context.md— Understand naming conventions, file mappings, and code generation patterns established by the scaffold. If missing, WARN: "Scaffold context not found. Proceed with manual directory scanning." - Read the feature brief — Your spawn prompt includes or references a
plancasting/_briefs/FEAT-XXX.mdfile. - Read PRD sections — Check
plancasting/prd/04-epics-and-user-stories.mdfor acceptance criteria (Given-When-Then),plancasting/prd/06-user-flows.mdfor E2E flow paths,plancasting/prd/14-testing-strategy.mdfor test strategy. - Read BRD security requirements — Check
plancasting/brd/13-security-requirements.mdfor auth and validation rules that E2E tests must verify. - Read the implementation — Examine the backend and frontend code that was just written.
- Check
plancasting/tech-stack.md— Use the specified test runner and testing libraries. Check theSession Languagesetting — write user-facing strings (UI labels, toast messages, error messages) in that language. Code and comments remain in English.
Scaffold Inventory
Before writing ANY test code, check for existing scaffold test files:
- Run
ls e2e/to identify existing files for this feature. - Check
plancasting/_scaffold-manifest.mdfor E2E test scaffold mappings. - If scaffold E2E files exist (from Stage 3 Teammate 5), implement inside them rather than creating new files. NEVER create duplicate files alongside scaffold files.
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 · 128 lines · 244 tokens per session scan A 4a7fcde76dcf
feature-tests is an agent published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 244 tokens to every session and 1,790 once invoked, about $0.0012 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.