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 commands/paulduvall/ai-development-patterns/implement-specgit clone --depth 1 https://github.com/PaulDuvall/ai-development-patternsWhat 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 | $0.00010 | $0.00916 |
| Opus 5 | $0.00005 | $0.00458 |
| Sonnet 5 | $0.00002 | $0.00183 |
| Haiku 4.5 | $0.00001 | $0.00092 |
Grade A, and why
implement-spec 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Specification
You are helping a developer implement a specification using test-driven development with full traceability from requirements to code. Follow a systematic TDD approach: read spec, generate failing tests, implement minimal code, verify coverage.
Usage
/implement-spec AUTH-001 # Implement authentication spec
/implement-spec PAYMENT-042 # Implement payment spec
Process
1. Read Specification
Read specification file from project specs directory:
- Location:
@specs/$1.md(e.g.,@specs/AUTH-001.md) - Parse specification structure:
- Requirements section
- Acceptance criteria
- Test cases
- Dependencies
2. Extract Acceptance Criteria
Identify all acceptance criteria from the specification:
- Format:
AC-001,AC-002, etc. - Extract expected behavior for each criterion
- Identify edge cases and error conditions
- Note any dependencies between criteria
3. Generate Failing Tests
Create test suite for each acceptance criterion:
- Write failing tests FIRST (Red phase)
- Test naming:
test_<spec_id>_<criterion_id>_<behavior> - Include docstring linking to spec:
"""Implements: specs/$1.md#AC-001""" - Cover happy path and error conditions
- Use realistic test data
Example:
def test_auth001_ac001_user_login_success():
"""Implements: specs/AUTH-001.md#AC-001
AC-001: User can log in with valid email and password
"""
user = create_test_user(email="[email protected]", password="SecurePass123")
result = login(email="[email protected]", password="SecurePass123")
assert result.success is True
assert result.token is not None
4. Implement Minimal Code
Write minimal implementation to pass tests:
- Follow test-driven development (TDD) approach
- Implement only what's needed to satisfy acceptance criteria
- Add traceability comments linking code to spec:
# Implements: specs/AUTH-001.md#AC-001 def login(email: str, password: str) -> LoginResult: # Implementation here
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 · 126 lines · 10 tokens per session scan A b48b7a6c4279
implement-spec is a command published in the GitHub repository PaulDuvall/ai-development-patterns (645 stars, last pushed 3d ago), licensed MIT. It adds 10 tokens to every session and 916 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 2026-08-30.
Other commands, from other repositories
paul:help
Show available PAUL commands and usage guide.
paul:handoff
Generate comprehensive session handoff document.
paul:plan-fix
Plan fixes for UAT issues from verify.
paul:research-phase
Research unknowns for a phase using subagents.
config
Manage PAUL project configuration and integrations. Create or update .paul/config.md at any point in the project lifecycle.
paul:progress
Smart status with routing - suggests ONE next action.