tidy

tidy is a skill for Claude Code, Codex from claudiodangelis/banco. It costs 71 tokens per session (1,419 once invoked), scanned C, original, MIT.

A guided workflow for finding Banco data that the current configuration no longer supports and deciding what to remove. Banco is a tool that syncs repositories, tasks, notes, and bookmarks.

In plain words
What is it for?
Running `banco tidy --pretty`, reviewing stale repositories, task trees, local notes or bookmarks, and unused module directories, then confirming any cleanup before deletion.
Why use it?
It shows what has become stale after configuration changes while keeping deletion under your control.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Running banco tidy --pretty, reviewing stale repositories, task trees, local notes or bookmarks, and unused module directories, then confirming any cleanup before deletion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/claudiodangelis/banco/tidy
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 claudiodangelis/banco --skill tidy
Clone the repo
git clone --depth 1 https://github.com/claudiodangelis/banco

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 tidy

README.md
[![agentmods](https://agentmods.dev/badge/skills/claudiodangelis/banco/tidy/github.svg)](https://agentmods.dev/skills/claudiodangelis/banco/tidy)
Your own site
<a href="https://agentmods.dev/skills/claudiodangelis/banco/tidy"><img src="https://agentmods.dev/badge/skills/claudiodangelis/banco/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.

agentmods 80×15 button for tidy

Your own site · 80×15
<a href="https://agentmods.dev/skills/claudiodangelis/banco/tidy"><img src="https://agentmods.dev/badge/skills/claudiodangelis/banco/tidy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,419 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00071 $0.01419
Opus 5 $0.00036 $0.00709
Sonnet 5 $0.00014 $0.00284
Haiku 4.5 $0.00007 $0.00142

Measured 10d ago against content hash 8df4fd2188ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

tidy scanned grade C 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

6. Remove only what the user confirms — `rm -rf` the reported `path`, or use the
src/skills/tidy/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tidy

Help the user remove banco data that the configuration no longer backs, while making sure nothing valuable is lost. The user always has the last word: never delete anything without explicit confirmation, and always surface what would be lost first.

How it works

Run banco tidy --pretty to get a JSON report of stale data. It is detection-only — it never deletes. The report has four arrays:

  • repos — repository directories no longer matching the config (remote, and repos/local when the repos module is turned off for the local provider)
  • tasks — task directories whose issues are no longer synced (remote, and tasks/local when the tasks module is turned off for the local provider)
  • local — local notes/bookmarks surfaced for review (only when you pass --module notes or --module bookmarks)
  • modules — whole module directories (repos/, tasks/, …) that no enabled provider backs anymore

To review a single module, pass --module <repos|tasks|notes|bookmarks>.

Workflow

  1. Run banco tidy --pretty.
  2. If everything is empty, tell the user there is nothing to tidy and stop.
  3. Group the findings by type and present them clearly (see below).
  4. For each item, state the reason and what would be lost.
  5. Ask the user what to remove. Default to keeping anything unsafe.
  6. Remove only what the user confirms — rm -rf the reported path, or use the appropriate command. Then report what was removed and what was kept.

Repos — check git safety before suggesting removal

Each repo finding has a reason and a git block. Never recommend deleting a repo whose git.safe_to_remove is false. Instead, warn the user about each non-empty field:

  • uncommitted_changes: true — modified tracked files not committed
  • untracked_files: N — N files git isn't tracking
  • unpushed_commits: N — N commits not on any remote (would be lost)
  • local_only_branches: [...] — branches with no upstream (may be unique work)
  • unmerged_branches: N — N local branches not merged into the current branch
  • stashes: N — N stash entries

Read the full file on GitHub · 125 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. 10d ago First seen · 125 lines · 71 tokens per session scan C 8df4fd2188ea

Subscribe to this mod's changes

tidy is a skill published in the GitHub repository claudiodangelis/banco (58 stars, last pushed 21d ago), licensed MIT. It adds 71 tokens to every session and 1,419 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

meegle

A guide and command-line interface for managing Feishu/Lark Meego project data, including work items, workflow steps, views, personal tasks, and schedules. Feishu/Lark is a collaboration platform, while Meego is its project-management system.

larksuite/meegle-cli · 126 tokens

project-ops

Use when an operator wants to run a small or mid-sized project from a flat file instead of standing up Jira or Asana — dated milestones each with one named owner and a binary done-test, rule-driven RAG status, a RAID log, slippage detection, and a two-minute weekly status report. NOT sequencing the engineering work…

ericrisco/rsc-harness · 80 tokens

jjj

Use when working in Jujutsu repositories for problem tracking, solution management, and code review — implements Popperian epistemology (problems → solutions → critiques) directly in version control.

doug/jjj · 40 tokens

metagit-projects

Ongoing workspace and project management for OpenClaw and Hermes agents. Use when starting work, organizing repos, or before creating a new project folder so existing metagit projects are reused instead of duplicated.

metagit-ai/metagit-cli · 45 tokens

metagit-rewrite-campaign

Orchestrate a reference-implementation rewrite across source and target repos using campaigns, parity registry conventions, objectives, and subagent handoffs.

metagit-ai/metagit-cli · 35 tokens

c-jira

Manage Jira issues using jira (jira-cli). List and filter issues, create new tickets, transition issue status, manage sprints, and add comments — all from the terminal without opening a browser.

daxaur/openpaw · 45 tokens