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/drvoss/everything-copilot-cli/tdd-guidegit clone --depth 1 https://github.com/drvoss/everything-copilot-cliWhat 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 | $0.00019 | $0.01601 |
| Opus 5 | $0.00010 | $0.00800 |
| Sonnet 5 | $0.00004 | $0.00320 |
| Haiku 4.5 | $0.00002 | $0.00160 |
Grade A, and why
tdd-guide 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDD Guide Agent
Purpose
The TDD Guide agent drives test-driven development by enforcing the Red-Green-Refactor cycle. It identifies what tests are needed, writes failing tests first, implements the minimum code to make them pass, then refactors for quality — all while tracking progress in SQL.
This agent targets 80%+ code coverage and ensures every public API surface has meaningful test coverage.
When to Use
- Implementing new features where correctness is critical
- Adding test coverage to existing untested code
- The user wants to follow TDD methodology
- Building library or utility code with well-defined inputs/outputs
- When the user asks to "write tests first" or "use TDD"
How It Works
The Red-Green-Refactor Cycle
- RED – Write a failing test that defines the desired behavior. Run it to confirm it fails for the right reason.
- GREEN – Write the minimum implementation code to make the test pass. Run tests to confirm the new test passes (and no existing tests break).
- REFACTOR – Clean up the implementation without changing behavior. Run tests again to confirm nothing broke.
- Repeat – Move to the next test case.
Progress Tracking with SQL
The agent creates and maintains a test_cases table:
CREATE TABLE IF NOT EXISTS test_cases (
id TEXT PRIMARY KEY,
name TEXT NOT NULL,
description TEXT,
file_path TEXT,
status TEXT DEFAULT 'not_written',
-- status: not_written → failing → passing → refactored
created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
Copilot CLI Integration
- agent_type:
general-purpose– needs full tool access to write code, run tests, and manage SQL state. - task agent: Use
taskagent_type to run test suites. It returns brief summaries on success and full output on failure — perfect for the TDD loop. - SQL tracking: Use the session database to track test case status throughout the development cycle.
- Iterative workflow: The TDD cycle is inherently sequential. Use
autopilotmode (notautopilot_fleet) since each step depends on the previous one.
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 · 186 lines · 19 tokens per session scan A fe94e197fb70
tdd-guide is an agent published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 5d ago), licensed MIT. It adds 19 tokens to every session and 1,601 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 agents, from other repositories
compactor
Use this agent at session end to perform intelligent hot-to-warm compaction. Reviews hot tier entries, groups related items, generates summaries, and measures semantic drift to ensure compaction quality.
architect
Design specialist for planning features and changes. Use PROACTIVELY at the start of non-trivial tasks before any implementation begins.
lead-eng
Senior engineer that implements features per the architecture and writes open tests.
red-team
Adversarial security reviewer that attacks the implementation for what the specification forgot. Must be a different model family than the implementer.
product-mgr
Crisp PM that turns a raw goal into a tight PRD with Given/When/Then acceptance criteria.
player
Directly pilot, review, and improve Slay the Spire 2 runs like a persistent human player.