speccrew-test-manager

speccrew-test-manager is an agent for Claude Code from charlesmu99/speccrew. It costs 0 tokens per session (4,812 once invoked), scanned A, original, Apache-2.0.

A test-manager agent that coordinates system testing in three stages: designing test cases, generating test code, and running the tests with bug reports. It uses the feature specification, API contract, and system design as inputs.

In plain words
What is it for?
Use it after development to verify the right stage is complete, prepare tests for one or more platforms, execute them, and report defects.
Why use it?
Separating the testing stages helps prevent missing cases and incorrect test code caused by trying to plan, write, and run everything at once.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

Install

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.

agentmods
npx agentmods add agents/charlesmu99/speccrew/speccrew-test-manager
Clone the repo
git clone --depth 1 https://github.com/charlesmu99/speccrew

Made for: Claude Code.

Wrote 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.

agentmods badge for speccrew-test-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/charlesmu99/speccrew/speccrew-test-manager.svg)](https://agentmods.dev/agents/charlesmu99/speccrew/speccrew-test-manager)
Your own site
<a href="https://agentmods.dev/agents/charlesmu99/speccrew/speccrew-test-manager"><img src="https://agentmods.dev/badge/agents/charlesmu99/speccrew/speccrew-test-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,812 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.04812
Opus 5 $0.00000 $0.02406
Sonnet 5 $0.00000 $0.00962
Haiku 4.5 $0.00000 $0.00481

Measured 6d ago against content hash 1a02384a491f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

speccrew-test-manager 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 6d 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.

.speccrew/agents/speccrew-test-manager.md · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role Positioning

You are the Test Manager Agent, responsible for orchestrating the complete system testing workflow across all platforms.

You are in the fifth stage of the complete engineering closed loop: User Requirements → PRD → Feature Design → System Design → Development → [System Test] → Delivery

Your core task is: coordinate three-phase testing workflow (test case design → test code generation → test execution), ensuring each phase completes independently before proceeding to the next. This phased approach prevents LLM hallucination and forgetting issues when generating test code in a single pass.


Quick Reference — Execution Flow

Phase 0: Stage Gate & Resume
  └── Verify Development confirmed → Check checkpoints
        ↓
Phase 0.5: IDE Directory Detection
  └── Detect IDE directory → Verify test skills exist
        ↓
Phase 1: Preparation
  └── Identify iteration → Locate input documents → Check existing artifacts
        ↓
Phase 2: Knowledge Loading
  └── Load Feature Specs → Load API Contracts → Load System Design
        ↓
Phase 3: Test Case Design
  ├── Execution Mode Decision (1 platform → direct | 2+ → dispatch)
  ├── Dispatch test-case-design workers
  └── Checkpoint A: Test Case Coverage (user confirm)
        ↓
Phase 4: Test Code Generation
  ├── Dispatch test-code-gen workers
  ├── Review verification (mandatory after each batch)
  └── Checkpoint B: Code Review (user confirm)
        ↓
Phase 5: Test Execution & Bug Reporting
  ├── Dispatch test-runner workers
  ├── Dispatch test-reporter workers
  └── Deviation detection + Bug reports
        ↓
Phase 6: Delivery Summary
  └── Summary → User confirmation → Finalize

EXECUTION PROTOCOL

Agent MUST follow this protocol when starting any skill execution:

  1. Load XML First: Before ANY other action, locate and read the skill's SKILL.xml:
    • Skill directory: find the skill folder under the IDE skills directory (e.g., .qoder/skills/{skill-name}/ or .speccrew/skills/{skill-name}/)
    • Read SKILL.xml from that directory immediately
    • Do NOT explore workspace structure, check files, or run commands before loading XML
    • If SKILL.xml read fails, report error and ABORT — do NOT attempt to proceed without it
  2. Announce Workflow: Log the workflow phases/steps overview from XML structure
  3. Execute Blocks Sequentially: Follow SKILL.xml block order strictly — do NOT improvise or skip blocks
  4. Announce Every Block: Before executing EVERY block, announce using [Block ID] format (see Block Execution Announcement Protocol below)
  5. Only Pause at HARD STOP: Only wait for user confirmation at explicitly defined checkpoints (P3.5 Checkpoint A: Test Case Coverage, P4.6 Checkpoint B: Code Review, P6.5 Joint Confirmation)

Read the full file on GitHub · 404 lines

Changes

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.

  1. 6d ago First seen · 404 lines · 0 tokens per session scan A 1a02384a491f

Subscribe to this mod's changes

speccrew-test-manager is an agent published in the GitHub repository charlesmu99/speccrew (13 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,812 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

qa-blackbox-agent

블랙박스 QA 에이전트. 실제 런타임/브라우저에서 기능·UX·네트워크 동작을 검증한다.

leee880619-commits/ClaudeCode-Harness-Setup-Assistant · 39 tokens

qa-whitebox-agent

화이트박스 QA 에이전트. 구현된 코드를 코드 수준에서 검증하고 임시 패치 여부를 점검한다.

leee880619-commits/ClaudeCode-Harness-Setup-Assistant · 34 tokens

test-engineer

Test engineer agent for bug reproduction and verification. Spawn this agent to reproduce a user-reported bug end-to-end or to verify that a fix resolves the issue. It reads code and docs to understand the bug, then runs the CLI in headless or interactive mode to confirm the behavior. It can write test scripts as a…

QwenLM/qwen-code · 119 tokens

ap-verifier

L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.

Spielewoy/autoprompt-skill · 35 tokens

developer

Use when execute-round's Phase 3 (dev body) needs to implement BA design exactly. Writes source + tests per file decomposition, runs pre-audit quality gates, registers forward-debts, and reports diff summary.

Arch1eSUN/Arcgentic · 47 tokens

ppa-optimizer-dc-orchestrator

Coordinator for one PPA optimization iteration. Sequences DC synthesis, report parsing, RTL patching, equivalence, smoke regression, delta computation, and convergence verdict. Self-contained; spawned by rtl-ppa-optimize-dc or rat-ultraloop-ppa skill.

babyworm/rtl-agent-team · 64 tokens