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 skills add djscheuf/agentic-dev-ecosystem-template --skill write-minimal-implementationgit clone --depth 1 https://github.com/djscheuf/agentic-dev-ecosystem-templateWrote 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/skills/djscheuf/agentic-dev-ecosystem-template/write-minimal-implementation)<a href="https://agentmods.dev/skills/djscheuf/agentic-dev-ecosystem-template/write-minimal-implementation"><img src="https://agentmods.dev/badge/skills/djscheuf/agentic-dev-ecosystem-template/write-minimal-implementation/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/skills/djscheuf/agentic-dev-ecosystem-template/write-minimal-implementation"><img src="https://agentmods.dev/badge/skills/djscheuf/agentic-dev-ecosystem-template/write-minimal-implementation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.00994 |
| Opus 5.5 | $0.00016 | $0.00398 |
| Sonnet 5.5 | $0.00008 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
write-minimal-implementation 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Steps
Step 1: Analyze the Failure
Review the test failure:
- What class/method is missing?
- What behavior is not implemented?
- What's the simplest fix?
Step 2: Write Minimal Implementation
CRITICAL: Write ONLY enough code to pass the test.
Acceptable approaches:
- Return a hardcoded value
- Implement the simplest algorithm
- Add the minimal structure needed
FORBIDDEN:
- Implementing features not tested
- Adding error handling not tested
- Optimizing prematurely
- Adding "obvious" code paths
Step 3: Make It Compile
If the test fails due to missing types/methods:
1. Create the class/interface if missing
2. Add method signatures with minimal body
3. Return default/hardcoded values initially
Example progression:
// Step 1: Make it compile
public class Calculator
{
public int Add(int a, int b) => 0; // Just compile
}
// Step 2: Make it pass
public class Calculator
{
public int Add(int a, int b) => 5; // Hardcoded for first test
}
Step 4: Run the Test
Execute ONLY the specific test:
- dotnet test --filter "TestName"
- pytest -k "test_name"
- npm test -- --grep "test name"
Verify:
✓ The specific test now passes
✓ No compilation errors
✓ Test passes for the right reason
// TODO - Add Run-Test Skill specific to the project's testing framework, supporting that projects structure.
Step 5: Run All Tests
Ensure no regressions:
- Run the entire test suite
- All tests should pass
- If any test fails, fix immediately
If new failures appear:
- Your change broke something
- Revert and reconsider approach
- Smaller steps needed
// TODO - Add Run-Test Skill specific to the project's testing framework, supporting that projects structure, and specifically declares how to run all of a projects/subprojects tests.
Step 6: Document the Success
Update the test plan and mark that test as "passing".
Step 7: Write the Sentinel File
- create
<input_parent>/.process/when needed and write{skill-name}.done.jsonthere; use the repository-root.process/only when no input path is supplied. The sentinel must not be removed after verification. - the sentinel file will follow @/schema/sentinel.schema.json.
- set the task field to "{skill-name}".
- the verify_params of the sentinel file will follow @/schema/verify-params.schema.json.
- set the verify_params as follows:
- set "test_cases_path" to the path of the test cases file relative to repo root.
- set "failing_test_path" to the path of the failing test file relative to repo root.
- set "failing_test_name" to the name of the failing test.
- set "changed_code_files" to an array of paths to all the changed code files relative to repo root.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed 7a440e2f73dc
- 1mo ago First seen · 142 lines · 41 tokens per session scan A cfa080dca801
write-minimal-implementation is a skill published in the GitHub repository djscheuf/agentic-dev-ecosystem-template (12 stars, last pushed 20d ago), licensed MIT. It adds 41 tokens to every session and 994 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
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.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…