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 commands/mikefluff/skills/tidygit clone --depth 1 https://github.com/Mikefluff/skillsWrote 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/commands/mikefluff/skills/tidy)<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>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 | $0.00000 | $0.01867 |
| Opus 5 | $0.00000 | $0.00933 |
| Sonnet 5 | $0.00000 | $0.00373 |
| Haiku 4.5 | $0.00000 | $0.00187 |
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.
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)
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.
- 3d ago First seen · 147 lines · 0 tokens per session scan A 6972eda9f1a5
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.
Other commands, from other repositories
clarity-interview
Co-write a piece with clarity, starting from an interview.
clarity-review
Review a draft with clarity, without rewriting it.
clarity-rewrite
Rewrite a draft with clarity.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.