tidy

tidy is a command for Claude Code from Mikefluff/skills. It costs 0 tokens per session (1,867 once invoked), scanned A, original, MIT.

A command for working through a defined set of remaining code-quality and verification tasks in a project whose quality baseline has no recorded exceptions.

In plain words
What is it for?
Use it to inspect the listed cleanup work and run the project's code-quality, validation, smoke, unit-test, documentation, and writer-snapshot checks.
Why use it?
It provides a fixed order of checks and highlights unfinished defects, missing committed tests, and required validation steps.

Command for Claude Code

Part of the mikefluff-skills plugin — 44 skills, 2 commands shipped together

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.

agentmods
npx agentmods add commands/mikefluff/skills/tidy
Clone the repo
git clone --depth 1 https://github.com/Mikefluff/skills

Made for: Claude Code.

Or install mikefluff-skills, the plugin that ships this one along with the rest of its 44 skills, 2 commands.

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 tidy

README.md
[![agentmods](https://agentmods.dev/badge/commands/mikefluff/skills/tidy.svg)](https://agentmods.dev/commands/mikefluff/skills/tidy)
Your own site
<a href="https://agentmods.dev/commands/mikefluff/skills/tidy"><img src="https://agentmods.dev/badge/commands/mikefluff/skills/tidy.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,867 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01867
Opus 5 $0.00000 $0.00933
Sonnet 5 $0.00000 $0.00373
Haiku 4.5 $0.00000 $0.00187

Measured 3d ago against content hash 6972eda9f1a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tidy 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 3d 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.

.claude/commands/tidy.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tidy — finish what the paydown left

The structural baseline is empty. scripts/code-quality-baseline.json has no entries, so every gate is live: a new violation is now a hard failure with nothing to hide behind. That is the regime this session works in.

What is left is not structure. It is four small defects, one unfinished verification job, and the fact that several proofs from the paydown were run as throwaway scripts instead of committed tests.

Argument (optional): a section letter from the table below. With no argument, work the table top-down.

Read first

python3 scripts/check-code-quality.py          # must print 0 known violations
make validate && make smoke && make test-unit && make check-docs
bash tests/run.sh                              # 31 writer snapshots
git log --oneline main..HEAD | head -25        # the paydown, if still unmerged

CONTRIBUTING.md §2b describes the gate. Thresholds: module ≤400 lines (≤900 for a module that declares only data — no def, no class), function ≤50, branch complexity ≤12, parameters ≤5.

The work

# Item Size Why it matters
A Platform limits still marked ~ 12 rows Start here. The only sweep item from the paydown never touched. Four of these numbers were already wrong once.
B Turn the equivalence probes into tests 3 files The paydown proved several refactors byte-identical with scripts that were then thrown away. The proof should live in the repo.
C Four known defects small Each found by reading during the paydown, each deliberately left alone mid-refactor.
D Remaining test gaps ~5 modules Ranked by what would actually catch something.

A — verify the platform limits

skills/post-publisher/references/platform-limits.md marks a row ~ when the number came from a vendor parameter table that could not be machine-read. Twelve rows carry it:

  • Telegram — 4096 / 1024 caption split (line 31), 10 MB sendPhoto (58)
  • X — 280 chars (35), 5 MB image / 512 MB video (62)
  • YouTube — 100 title / 5000 description / ~500 tag chars (36), 256 GB / 12 h (63)
  • LinkedIn — 3000 chars, 4086 altText (37), 10 MB / 500 MB (64)
  • Threads — 1 GB video, explicitly "not stated in the docs read" (59)
  • TikTok — 20 MB image (61)

Read the full file on GitHub · 147 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. 3d ago First seen · 147 lines · 0 tokens per session scan A 6972eda9f1a5

Subscribe to this mod's changes

tidy is a command published in the GitHub repository Mikefluff/skills (18 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,867 tokens. 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.