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.
git clone --depth 1 https://github.com/marcoemrich/agentic_coding_labWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/marcoemrich/agentic_coding_lab/green)<a href="https://agentmods.dev/commands/marcoemrich/agentic_coding_lab/green"><img src="https://agentmods.dev/badge/commands/marcoemrich/agentic_coding_lab/green/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/marcoemrich/agentic_coding_lab/green"><img src="https://agentmods.dev/badge/commands/marcoemrich/agentic_coding_lab/green.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00930 |
| Opus 5.5 | $0.00000 | $0.00372 |
| Sonnet 5.5 | $0.00000 | $0.00186 |
| Haiku 4.5 | $0.00000 | $0.00093 |
Grade A, and why
green 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 1mo 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.
This is a copy
88% identical to green — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDD Green Phase
You are now in the Green Phase of TDD. Follow these instructions to make the failing test pass with MINIMAL code.
Your Mission
- Implement the minimal code necessary to make the failing test pass
- Use the simplest possible solution (hardcoded values are acceptable)
- Avoid adding features for future tests
- Verify all tests pass
- NO optimization, NO refactoring yet
Context: $ARGUMENTS
Green Phase Rules
- Minimal code only: Just enough to pass the current test
- Baby steps: Make the smallest possible change
- No future features: Don't implement what future tests might need
- Simple is better: Hardcoded returns are perfectly fine
- Tests must pass: Verify all tests are green
- No refactoring yet: Save improvements for Refactor phase
Process
Step 1: Analyze the Failing Test
Understand what the test expects:
- What input does the test provide?
- What output does it expect?
- What is the simplest way to produce that output?
Step 2: Write Minimal Implementation
Implement only what's needed to make the current test pass:
// For first test "should return 0 for empty input":
export const calculate = (input: string): number => {
return 0; // Minimal - just make the test pass
};
// For second test "should return number for single input":
export const calculate = (input: string): number => {
if (input === "") return 0;
return parseInt(input); // Still simple
};
// For third test "should add two numbers":
export const calculate = (input: string): number => {
if (input === "") return 0;
const numbers = input.split(",");
if (numbers.length === 1) return parseInt(numbers[0]);
return parseInt(numbers[0]) + parseInt(numbers[1]); // Only now add logic
};
Step 3: Run Tests
Run pnpm test:unit:basic and verify:
- Current test now passes ✅
- All previous tests still pass ✅
Step 4: Verify No Over-Implementation
Check yourself:
- ❓ Did I implement features for future tests? → Remove them
- ❓ Did I add logic not demanded by current test? → Remove it
- ❓ Did I optimize prematurely? → Simplify
- ❓ Did I refactor existing code? → Revert, save for Refactor 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.
- 1mo ago First seen · 135 lines · 0 tokens per session scan A 2b6cdd5a8d00
green is a command published in the GitHub repository marcoemrich/agentic_coding_lab (13 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 930 tokens. A static security scan graded it A with 0 findings. It is 88% identical to green, differing in 7 lines, and is treated as a copy.
Other commands, from other repositories
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
usage-add
PitWay: Accumulate measured planning or qa token usage onto a milestone.
speckit.tdd.plan
Derive the feature's test list by delegating to zfa tdd plan (deterministic engine); falls back to LLM-guided derivation only when zfa is unavailable.
tdd
A command that follows test-driven development (TDD), a method where you write tests before the code they check. It moves through writing a failing test, adding the smallest implementation, and then improving the code.
dashboard
Generar dashboard HTML local con métricas de eficiencia del proyecto SDD.