A file-tree cleanup review that finds loose scripts, unused code, logs, caches, and unexplained scratch files. It gathers evidence about each item before suggesting what to do.

Use it to organize repository files, identify obsolete code or runtime clutter, and decide whether items should be kept, moved, or deleted.

It removes uncertainty about which files belong in a repository and which are leftovers. Deletions and other changes are separated for approval.

keel-tidy — Skill for Claude Code by muratsilahtaroglu

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 muratsilahtaroglu/claude-code-starter-kit --skill keel-tidy

Clone the repo

git clone --depth 1 https://github.com/muratsilahtaroglu/claude-code-starter-kit

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-tidy/github.svg)](https://agentmods.dev/skills/muratsilahtaroglu/claude-code-starter-kit/keel-tidy)

Your own site

<a href="https://agentmods.dev/skills/muratsilahtaroglu/claude-code-starter-kit/keel-tidy"><img src="https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-tidy/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/muratsilahtaroglu/claude-code-starter-kit/keel-tidy"><img src="https://agentmods.dev/badge/skills/muratsilahtaroglu/claude-code-starter-kit/keel-tidy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,329 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.

Model	Per session	Once invoked
Fable 5.1	$0.00104	$0.01329
Opus 5.5	$0.00042	$0.00532
Sonnet 5.5	$0.00021	$0.00266
Haiku 4.5	$0.00010	$0.00133

Measured 2mo ago against content hash 169494e68b46, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

keel-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 2mo 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/skills/keel-tidy/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/keel-tidy — the §3.10 sweep: no file left unanswered

When: layout drift is felt (loose files at the repo root, stray one-off scripts, logs/caches in the tree, scratch/ overflowing), at a phase boundary, or every ~5 sessions as hygiene. This is the ritual arm of rules.md §3.10 — "no file of unclear purpose is left in the main source tree". It is NOT /keel-distill's job: distill curates the MEMORY files (§9 caps), tidy curates the FILE TREE (§3 layout) — different axis, different risk, and a file sweep bolted onto a cap rotation would derail both.

1. Sweep — collect candidates deterministically

Repo-root files outside the discipline scaffold (CLAUDE.md · rules.md · HANDOVER/LESSONS/TASKS/ PLAN · README/LICENSE/CONTRIBUTING · Makefile/pyproject/lockfiles · dotfiles) — §3.10: the root holds scaffold only; application code lives under src/.
Runtime junk anywhere: *.log · *.tmp · __pycache__/ · .pytest_cache/ · editor swap files · stray outputs sitting outside reports/.
scratch/ items NOTHING CITES. The criterion is citation, NOT age: a probe named by a reports/ note, ADR or doc is that claim's permanent EVIDENCE (§10.40) and stays put however old it is (field case: a probe untouched for 18 days was the independent measurement behind that week's decision). Check BOTH directions — grep -rl "scratch/<name>" reports/ docs/ *.md for path citations, then grep -rl "<name>" reports/ for the report whose FILENAME carries the id; a path-only check reported a live folder as dead on a real project. Also flag any scratch file missing its 1-line purpose comment (§3.10) — that one IS a per-file check.
Source files nothing references: not imported (grep the module name across src/ + tests/), absent from Makefile/CI, not collected by the test runner, no docs/architecture.md row.

Off-limits (other jurisdictions): memory files + docs/adr/ (distill / the owner) · reports/ (the §2.8 evidence trail — prune only on an explicit ask) · research/ findings (§8.30) · tests/fixtures/ golden sets (§10.39) · paths already git-ignored.

Read the full file on GitHub · 67 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.

2mo ago First seen · 67 lines · 104 tokens per session scan A 169494e68b46

Subscribe to this mod's changes

keel-tidy is a skill published in the GitHub repository muratsilahtaroglu/claude-code-starter-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 1,329 once invoked, about $0.0004 per session on Opus 5.5. 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.

Claude Code LLM ai-agents developer-tools developer-tools-ai-agent project-template

duckduckgo-search

Free keyless web, news, and image search via ddgs.

NousResearch/hermes-agent · 19 tokens

mcporter

List, auth, and call MCP servers/tools from the terminal.

NousResearch/hermes-agent · 16 tokens

article-writing

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

affaan-m/ECC · 57 tokens

mem0-oss-to-platform

Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…

mem0ai/mem0 · 217 tokens

safe-refactor

Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.

JuliusBrussee/caveman · 29 tokens

create-tech-design

Only use when the user explicitly invokes this skill by name.

humanlayer/humanlayer · 16 tokens