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 skills/t1/tdder/project-hygienenpx skills add t1/tdder --skill project-hygienegit clone --depth 1 https://github.com/t1/tdderWrote 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/t1/tdder/project-hygiene)<a href="https://agentmods.dev/skills/t1/tdder/project-hygiene"><img src="https://agentmods.dev/badge/skills/t1/tdder/project-hygiene.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.01281 |
| Opus 5 | $0.00023 | $0.00641 |
| Sonnet 5 | $0.00009 | $0.00256 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
project-hygiene scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
*Always* prefer to use the `WebFetch` tool over `curl`. How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Hygiene
Cross-cutting conventions for disciplined agent-assisted development.
NEVER EVER PUBLISH ANYTHING No git push no maven deploy no npm publish,
or anything similar. All that is the user's privilege!
Interaction Style
- Always give brief, to-the-point, and concise answers; a single-line answer is often perfectly fine!
- Generally follow the YAGNI principle: don't hypothesise about long term consequences.
- Be critical and honest. The user can always be wrong, and it's not impolite to say so.
- When the user asks a question, it's just a question, not a suggestion. Don't start working on it — think about it and discuss.
- Never apologize for mistakes. Identify the root cause, find a solution, and explain how to prevent recurrence.
- Never use local/private auto memory. Store all learnings and conventions in project files
(e.g.
CLAUDE.md,README.md), so they are shared with everyone working on the project.
Commits
- Keep commit messages short (single line, no body).
- Never add a
Co-Authored-Bytrailer. - Squash related commits into one before finishing a task (e.g. a plan's worth of work becomes a single commit).
Documentation
Don't forget to update the documentation when you change the code. If a behavioral change affects README, API docs, or inline doc comments, update them in the same commit as the code change.
Skill Trust
Before writing or editing any code — including one-line fixes — invoke the matching
language/framework skill (e.g. java for .java files). No exception for "quick" edits.
Skills encode conventions (imports, naming, idioms) that apply to every change, not just big tasks.
Never look into library source code (e.g. JARs, node_modules) when a skill covers that library. The skill is the authoritative reference. If the skill is missing something, report it so the skill can be updated — don't work around it by reading source.
VERY IMPORTANT: if any skill you where instructed to load can't be loaded, stop immediately! Something's wrong that needs to be fixed first.
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.
- 5d ago First seen · 107 lines · 46 tokens per session scan A d2b1ba180133
project-hygiene is a skill published in the GitHub repository t1/tdder (14 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 1,281 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
tdd-arrange-act-assert
This skill should be used when the user asks to "structure tests", "organize test code", mentions "arrange act assert", "AAA pattern", "given when then", discusses test readability, or wants to improve test structure.
tdd-red-green-refactor
This skill should be used when the user asks to "do TDD", "write tests first", mentions "red-green-refactor", discusses test-driven development cycles, or wants to build features incrementally with tests.
tdd-test-first
This skill should be used when the user asks to "write tests first", "start with a test", mentions "test-first development", discusses writing tests before implementation, or wants to ensure code is testable by design.
testing-principles
Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.
develop-tdd
Test-driven development with red-green-refactor loop using vertical slices. Use for features (epic tasks) or bugs (specs/bugs/BUG-.md).
validate-fix
Prove a fix works before declaring done — re-run the failing test, run the full suite, typecheck, lint, and harden against recurrence. Use after implementing a bug fix, when user says "is this fixed?", or before closing an investigation.