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 skills/metaschema-framework/claude-plugins/development-workflownpx skills add metaschema-framework/claude-plugins --skill development-workflowgit clone --depth 1 https://github.com/metaschema-framework/claude-pluginsWhat 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 | $0.00028 | $0.01722 |
| Opus 5 | $0.00014 | $0.00861 |
| Sonnet 5 | $0.00006 | $0.00344 |
| Haiku 4.5 | $0.00003 | $0.00172 |
Grade A, and why
development-workflow 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Workflow
Scope: This document describes development workflows for AI agents (Claude + superpowers plugin) and automated code review. Human developers should adapt these TDD, parallel-execution, and review principles to their tooling and IDE.
Skill Usage Protocol (MANDATORY)
Before responding to ANY task, complete this checklist:
- Check for relevant skills - Does any skill match this request?
- If skill exists → Use
Skilltool to load and run it - Announce usage - "I'm using [skill] to [action]"
- Follow skill exactly - Don't adapt away the discipline
Checklist Tracking Rule
If a skill has a checklist, create TodoWrite todos for EACH item. Never:
- Work through checklists mentally
- Skip todos "to save time"
- Batch multiple items into one todo
Common Rationalizations (RED FLAGS)
If you think any of these, STOP and check for skills:
- "This is just a simple question"
- "Let me gather information first"
- "This doesn't need a formal skill"
- "The skill is overkill for this"
- "I'll just do this one thing first"
Why: Skills document proven techniques. Not using available skills = repeating solved problems.
Test-Driven Development (MANDATORY - BLOCKING)
ALL code changes MUST follow TDD. No exceptions. This is BLOCKING.
The Iron Law of TDD
TESTS MUST BE WRITTEN AND FAIL BEFORE ANY IMPLEMENTATION CODE EXISTS
This is non-negotiable. Implementation code written before tests is a violation.
The TDD Cycle
- Write the test first - Before writing any implementation code
- Watch it fail - Run the test to verify it fails for the right reason
- Write minimal code - Implement just enough to make the test pass
- Refactor - Clean up while keeping tests green
- Repeat - For each new behavior
Enforcement Gate
Before writing ANY implementation code, you MUST have:
- A test file created for the new functionality
- At least one failing test that exercises the code path
- Verification that the test fails for the expected reason (not a syntax error)
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 · 204 lines · 28 tokens per session scan A 8826e8c2066e
development-workflow is a skill published in the GitHub repository metaschema-framework/claude-plugins (10 stars, last pushed 6mo ago), licensed CC0-1.0. It adds 28 tokens to every session and 1,722 once invoked, about $0.0001 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 skills, from other repositories
agent-integration
Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last). For individual phases, use /agent-integration:research, /agent-integration:write-tests, or /agent-integration:implement. Use when the user says "integrate agent", "add agent…
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
code-assist
Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
css-design-tdd
Test-driven CSS design system modifications. Run checks before/after CSS changes to verify token usage, variable definitions, fallbacks, and consistency. Use when modifying CSS tokens, fixing design inconsistencies, or auditing CSS architecture.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.