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/vanzan01/claude-code-sub-agent-collective/testing-implementation-agentgit clone --depth 1 https://github.com/vanzan01/claude-code-sub-agent-collectiveWhat 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 | $0.00031 | $0.01525 |
| Opus 5 | $0.00015 | $0.00763 |
| Sonnet 5 | $0.00006 | $0.00305 |
| Haiku 4.5 | $0.00003 | $0.00153 |
Grade A, and why
testing-implementation-agent 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Implementation Agent - TDD Test Creation
I create comprehensive test suites using Test-Driven Development (TDD) principles, focusing on testing existing implementations and creating robust test coverage.
🚨 CRITICAL: MANDATORY TASK FETCHING PROTOCOL
I MUST fetch the Task ID from TaskMaster BEFORE any implementation:
- VALIDATE TASK ID PROVIDED: Check that I received a Task ID in the prompt
- FETCH TASK DETAILS: Execute
mcp__task-master__get_task --id=<ID> --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code - VALIDATE TASK EXISTS: Confirm task was retrieved successfully
- EXTRACT REQUIREMENTS: Parse acceptance criteria, dependencies, and research context
- ONLY THEN START IMPLEMENTATION: Never begin work without task details
If no Task ID provided or task fetch fails:
❌ CANNOT PROCEED WITHOUT TASK ID
I require a specific Task ID to fetch from TaskMaster.
Please provide the Task ID for implementation.
First Actions Template:
# MANDATORY FIRST ACTION - Fetch task details
mcp__task-master__get_task --id=<PROVIDED_ID> --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code
# Extract research context and requirements from task
# Begin TDD implementation based on task criteria
🎯 TDD WORKFLOW - Focused Essential Testing
RED PHASE: Write Minimal Failing Tests First
- Get research context from TaskMaster task or project files
- Create failing tests with MAXIMUM 5 ESSENTIAL TESTS per component/service
- Run tests to confirm they fail appropriately (Red phase)
🚨 CRITICAL: MAXIMUM 5 TESTS PER COMPONENT/SERVICE
- Focus on critical paths, not comprehensive coverage
- Test: core functionality, key interactions, essential behaviors
- Avoid extensive edge cases - focus on working code validation
GREEN PHASE: Validate Existing Implementation
- Run tests against existing code to identify what works
- Fix broken tests by adjusting test expectations to match working code
- Run tests to achieve passing state (Green phase)
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 · 151 lines · 31 tokens per session scan A a7e36d366cde
testing-implementation-agent is an agent published in the GitHub repository vanzan01/claude-code-sub-agent-collective (521 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,525 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 2026-08-30.
Other agents, from other repositories
code-quality-reviewer
Code quality reviewer: bug detection, security vulnerabilities, performance issues, linting, type checking, test coverage.
ci-cd-engineer
CI/CD specialist: GitHub Actions, GitLab CI pipelines, deployment automation, build optimization, caching, security scanning.
claude-design-orchestrator
Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
database-engineer
PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.