project-config-and-tests

project-config-and-tests is a skill for Claude Code, Codex from n-n-code/n-n-code-skills. It costs 37 tokens per session (534 once invoked), scanned A, original, MIT.

A project guide for configuration behavior and deterministic tests around it, including input sources, precedence, defaults, parsing, normalization, and path handling.

In plain words
What is it for?
Use it to define configuration rules, preserve safe help and recovery paths, decide when to fail, and test configuration boundaries.
Why use it?
It prevents unclear or inconsistent behavior when settings are missing, empty, malformed, unsupported, or supplied from multiple places.

Skill for Claude CodeCodex

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

Good fit Use it to define configuration rules, preserve safe help and recovery paths, decide when to fail, and test configuration boundaries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/n-n-code/n-n-code-skills/project-config-and-tests
Install

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.

Any agent
npx skills add n-n-code/n-n-code-skills --skill project-config-and-tests
Clone the repo
git clone --depth 1 https://github.com/n-n-code/n-n-code-skills

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 project-config-and-tests

README.md
[![agentmods](https://agentmods.dev/badge/skills/n-n-code/n-n-code-skills/project-config-and-tests.svg)](https://agentmods.dev/skills/n-n-code/n-n-code-skills/project-config-and-tests)
Your own site
<a href="https://agentmods.dev/skills/n-n-code/n-n-code-skills/project-config-and-tests"><img src="https://agentmods.dev/badge/skills/n-n-code/n-n-code-skills/project-config-and-tests.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 534 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 $0.00037 $0.00534
Opus 5 $0.00018 $0.00267
Sonnet 5 $0.00007 $0.00107
Haiku 4.5 $0.00004 $0.00053

Measured 2d ago against content hash 4c058446b382, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

project-config-and-tests 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.

.agents/skills/project-config-and-tests/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Config And Tests

This is a composable project overlay, not a standalone implementation workflow. Use it with matching language or discipline guidance when the main task is a configuration contract or deterministic tests at that boundary.

For review, inspect these contracts and report findings without editing config, tests, or process state. For implementation, apply only the requested changes and use isolated fixtures for validation.

When to use

The task involves configuration sources or precedence, defaults, parsing, normalization, path resolution, or deterministic tests around those seams.

Not for

Do not use this for general feature work (use the matching principle skill and add project-core-dev only when repository-specific completion evidence is not concrete), general test strategy (tester-mindset), framework-specific test implementation, vendored dependency changes (project-vendor-boundary), release-only work (project-release-maintainer), or environment diagnosis whose cause has not been isolated (project-platform-diagnose).

Workflow

  1. Establish the contract before editing: sources, precedence, defaults, and the behavior of missing, empty, malformed, and unsupported values.
  2. Preserve help, version, and recovery paths when they can operate safely without valid config. Fail fast or fail closed when continuing would be unsafe or would silently apply misleading behavior.
  3. Separate pure parsing and normalization from environment, filesystem, and process-global lookup when the existing design permits it.
  4. Make tests independent of ambient environment, current directory, user home, wall-clock time, and shared filesystem state. Use the repo's fixtures and temporary-directory helpers, and clean up any remaining state.
  5. Cover precedence and representative missing, empty, invalid, override, relative, absolute, and platform-sensitive path cases that belong to the supported contract. Do not simulate unsupported platforms and present the result as observed evidence.
  6. Keep defaults, example config, help text, and documentation aligned. Avoid printing secret values in diagnostics or test output.

Read the full file on GitHub · 57 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. 2d ago Changed · +4 lines 4c058446b382
  2. 7d ago First seen · 53 lines · 37 tokens per session scan A 2dbd8aea40e2

Subscribe to this mod's changes

project-config-and-tests is a skill published in the GitHub repository n-n-code/n-n-code-skills (4 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 534 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.