nixos-config: Skill for Claude Code

.agents/skills/issue-tdd/SKILL.md

issue-tdd is a skill for Claude Code, Codex from FilipNowakowicz/nixos-config. It costs 46 tokens per session (648 once invoked), scanned A, original, MIT.

A workflow for turning a vague issue or goal into a precise implementation plan before coding. TDD here means test-driven issue definition: the issue states the problem, acceptance checks, limits, risks, and open decisions.

In plain words
What is it for?
Use it to prepare GitHub issues, roadmap items, bug reports, or rough goals for implementation by adding concrete acceptance criteria and validation steps.
Why use it?
It prevents developers from starting work with unclear requirements or no agreed way to verify the result.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is FilipNowakowicz/nixos-config's own configuration. It tells Claude Code and Codex how to work on nixos-config itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nixos-config configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FilipNowakowicz/nixos-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/FilipNowakowicz/nixos-config/main/.agents/skills/issue-tdd/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/FilipNowakowicz/nixos-config

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for issue-tdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/filipnowakowicz/nixos-config/issue-tdd/github.svg)](https://agentmods.dev/skills/filipnowakowicz/nixos-config/issue-tdd)
Your own site
<a href="https://agentmods.dev/skills/filipnowakowicz/nixos-config/issue-tdd"><img src="https://agentmods.dev/badge/skills/filipnowakowicz/nixos-config/issue-tdd/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.

agentmods 80×15 button for issue-tdd

Your own site · 80×15
<a href="https://agentmods.dev/skills/filipnowakowicz/nixos-config/issue-tdd"><img src="https://agentmods.dev/badge/skills/filipnowakowicz/nixos-config/issue-tdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 648 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00648
Opus 5 $0.00023 $0.00324
Sonnet 5 $0.00009 $0.00130
Haiku 4.5 $0.00005 $0.00065

Measured 10d ago against content hash 84a24a56b5f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

issue-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 10d 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.

.agents/skills/issue-tdd/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue TDD

Use this before implementation when an issue or goal is not yet precise enough to build safely. The output is an updated GitHub issue body/comment or a scoped proposal for the user to approve.

Goal

Turn a vague goal into a testable issue:

  • problem statement
  • desired outcome
  • acceptance criteria
  • non-goals
  • likely touched files or modules
  • smallest meaningful validation command
  • risks and rollback/deploy concerns
  • outcome-changing questions for the user

Workflow

  1. Read the source item.
    • Use gh issue view <number> for GitHub issues.
    • For roadmap items, read the linked doc section and nearby context.
  2. Inspect only enough repo context to scope the work.
    • Use repo-map-query before broad exploration when relevant files are not obvious.
    • Do not start implementation.
  3. Draft the issue in implementation-ready form.
    • Use issue-driven-development for acceptance criteria and proving checks.
    • Use nix-verification-loop to choose validation when the touched surface is Nix, shell, docs, host, package, deploy, or profile-test related.
  4. Ask only real decisions before implementation.
    • Ask about security posture, ownership, deploy risk, product behavior, document ownership, or PR split boundaries.
    • Do not ask permission to inspect the repo, run normal validation, or proceed through routine workflow steps.
  5. Update the GitHub issue when asked, or return a paste-ready issue body/comment.

Decision Gate

If a decision changes the implementation, stop and ask before coding. Use this shape:

I need one decision before this is implementation-ready:

1. <question>
   Impact: <what changes depending on the answer>

Ask at most three questions at once. If there are no blocking decisions, say the issue is ready for issue-driven-development.

Issue Template

## Problem

...

## Desired outcome

...

## Acceptance criteria

- ...

## Non-goals

- ...

## Likely files

- ...

## Validation

- `...`

## Risk / Rollback

- ...

## Decisions

- [ ] ...

Read the full file on GitHub · 108 lines

Changes

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.

  1. 10d ago First seen · 108 lines · 46 tokens per session scan A 84a24a56b5f0

Subscribe to this mod's changes

issue-tdd is a skill published in the GitHub repository FilipNowakowicz/nixos-config (5 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 648 once invoked, about $0.0002 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.