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/drag88/claude-dev-framework/tddgit clone --depth 1 https://github.com/drag88/claude-dev-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 | $0.00015 | $0.00839 |
| Opus 5 | $0.00008 | $0.00419 |
| Sonnet 5 | $0.00003 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
tdd 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 yesterday.
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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cdf:tdd — Test-Driven Development
The TDD invariant
Write the failing test before any implementation code. Verify the test fails for the expected reason. Then write the minimum code to pass it.
This invariant is enforced because TDD's value comes from the RED phase — if you skip it, you have tests-after-code, not TDD.
First actions (per feature)
- Create the TDD state file at
dev/active/[feature-slug]/tdd-state.md:
---
feature: "[feature description]"
created: [ISO timestamp]
current_phase: red
cycle: 1
tests_written: 0
coverage_target: 80
---
# TDD: [Feature]
## Cycle 1
- [ ] RED: Write failing test
- [ ] RED: Verify test fails correctly
- [ ] GREEN: Write minimal implementation
- [ ] GREEN: Verify test passes
- [ ] REFACTOR: Improve code quality
- [ ] REFACTOR: Verify still green
-
Write the test file first. Create a failing test before any implementation exists.
-
Verify RED. Run the test and confirm it fails for the expected reason. Paste the failure output. Do not proceed to GREEN until the failure is documented.
Anti-patterns
- Writing implementation before the test exists (no RED state to verify)
- Writing a test that passes immediately (no failing baseline)
- Skipping failure verification (the RED output is the contract)
- Proceeding to GREEN without a documented RED phase
- Refactoring without re-running the full test suite
Triggers
- TDD workflow requests for new features or bug fixes
- Test-first development methodology needs
- Code quality improvement through testing discipline
- Coverage gate enforcement requirements
Usage
/cdf:tdd [feature-description] [--coverage <percentage>] [--strict]
Arguments
feature-description: What you want to implement using TDD--coverage <percentage>: Minimum coverage required (default: 80%)--strict: Enforce strict TDD - fail if tests written after code
Cycle Iteration
After completing RED → GREEN → REFACTOR:
- Add next test case (edge cases, error conditions)
- Repeat the cycle
- Continue until feature is complete
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.
- yesterday First seen · 134 lines · 15 tokens per session scan A 97a3726c8ca3
tdd is a command published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 839 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.