Agent skill

Todos Cleanup

by hanamizuki in hanamizuki/solopreneur

Batch cleanup of backlog todos — checks which items are already completed or partially done by searching git history, then moves them to done/ or doing/.

MITAuto-check passedDevelopment

Install Todos Cleanup

skills CLI
$ npx skills add hanamizuki/solopreneur --skill todos-cleanup -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hanamizuki/solopreneur todos-cleanup --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hanamizuki/solopreneur.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/solopreneur/todos-cleanup .claude/skills/todos-cleanup && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
todos-cleanup
GitHub stars
152
Token cost
~1.5k tokens
SKILL.md length
306 words
Files
1
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

Batch cleanup of backlog todos — checks which items are already completed or partially done by searching git history, then moves them to done/ or doing/.

  • Works in 4 steps: Gather file list → Spawn sonnet subagent for analysis → Present results and confirm → …
  • The user says cleanup todos
  • SKILL.md covers Config Discovery, Classification Rules, Workflow and Important
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Todos Cleanup is an agent skill from hanamizuki/solopreneur. Batch cleanup of backlog todos — checks which items are already completed or partially done by searching git history, then moves them to done/ or doing/. Use when the user says "cleanup todos", "triage backlog", "clean up backlog", "check todos status", or wants to classify backlog items based on actual implementation status.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Git workflow. The repository describes itself as: Skills and agents for solopreneurs — ship, review, debug, and think through problems with AI. The licence is MIT.

When your agent uses it

  • The user says cleanup todos
  • Clean up backlog
  • Check todos status
  • Wants to classify backlog items based on actual implementation status

Example prompts

  • “cleanup todos”
  • “triage backlog”
  • “clean up backlog”
  • “/todos-cleanup”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Gather file list
  2. Spawn sonnet subagent for analysis
  3. Present results and confirm
  4. Move files

What it can do on your machine

Read from SKILL.md and the folder at commit f43f001. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Todos Cleanup loads about 1.5k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 306 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hanamizuki/solopreneur at commit f43f001, republished under its MIT licence (© hanamizuki). 306 words, ~1,516 tokens.

Download SKILL.mdSave it as .claude/skills/todos-cleanup/SKILL.md (or your agent's skills folder).
name
todos-cleanup
description
Batch cleanup of backlog todos — checks which items are already completed or partially done by searching git history, then moves them to done/ or doing/. Use when the user says "cleanup todos", "triage backlog", "clean up backlog", "check todos status", or wants to classify backlog items based on actual implementation status.

Todos Cleanup

Scan the backlog directory and classify each item by checking git history for related commits. Present findings for user confirmation, then move files.

Config Discovery

Before scanning, resolve the todo directory paths. Source the config helpers first:

bash
# --- solopreneur config helpers (sourced from shared/config.sh) ---
# One real shell file, so no harness rewrites the helpers on the way to the
# shell. Claude Code replaces the ${CLAUDE_SKILL_DIR} token below when it loads
# this body; Codex does not. It is SINGLE-quoted on purpose — it is a load-time
# token, not an environment variable, and letting the shell expand the name
# would source whatever an inherited value happened to point at. Unreplaced, it
# is not a directory, so substitute the absolute path of the directory holding
# THIS SKILL.md — every harness states that path to the model.
SOLO_SKILL_DIR='${CLAUDE_SKILL_DIR}'
[ -d "$SOLO_SKILL_DIR" ] || SOLO_SKILL_DIR="<absolute path of the directory holding this SKILL.md>"
SOLO_CONFIG_SH="$SOLO_SKILL_DIR/../../shared/config.sh"
# Three candidates, one contract. Inside the plugin the helpers sit at ../../shared/;
# authoring against this repo reaches them under src/solopreneur/shared/; and a
# skill republished on its own — any flattened skills directory — carries them
# at scripts/config.sh instead, because shared/ is a sibling of skills/ and does
# not travel with a per-skill copy. Try each in order, then STOP. Sourcing a
# file that is not there does not halt the shell: every helper stays undefined,
# every config read returns empty, and the 2026-08-11 A2 run showed where that
# leads — the model "rescued" it with a repo-relative path, which resolves only
# when the repo under review happens to be this plugin's own source repo.
# Canonical authoring keeps non-skill source under src/.
[ -f "$SOLO_CONFIG_SH" ] || SOLO_CONFIG_SH="$SOLO_SKILL_DIR/../../../src/solopreneur/shared/config.sh"
[ -f "$SOLO_CONFIG_SH" ] || SOLO_CONFIG_SH="$SOLO_SKILL_DIR/scripts/config.sh"
[ -f "$SOLO_CONFIG_SH" ] || { echo "HALT: solopreneur config helpers not found under $SOLO_SKILL_DIR — stop here, do not improvise a path"; exit 1; }
source "$SOLO_CONFIG_SH"
# --- end solopreneur config helpers ---
  1. Check plugin config:

    bash
    read_solopreneur_config todos

    If the todos key exists, use its backlog, done, doing, later values.

  2. If no config — scan the project: Search for directories that look like todo/task storage:

    bash
    # Common patterns
    find . -maxdepth 3 -type d \( -name "todos" -o -name "todo" -o -name "TODO" \
      -o -name "backlog" -o -name "tasks" -o -name ".todos" \) 2>/dev/null

    For each candidate, count .md files inside. Present findings:

    Found potential todo directories:
      a) todos/backlog/ (12 .md files)
      b) tasks/ (5 .md files)
    Which is your backlog directory? (or enter a custom path)
  3. Save to config after user confirms. Discovered paths are repo-relative (todos/backlog etc.), so the per-repo write helper anchors them to this repo's entry:

    bash
    write_solopreneur_repo_config todos '{
      "backlog": "todos/backlog",
      "done": "todos/done",
      "doing": "todos/doing",
      "later": "todos/later"
    }'

    Substitute user-confirmed paths into the JSON. Each repo gets its own entry — running this skill in a different repo will not clobber this one's setting.

Use the resolved paths for all subsequent steps. Variables below:

  • $BACKLOG — backlog directory (e.g., todos/backlog)
  • $DONE — done directory (e.g., todos/done)
  • $DOING — doing directory (e.g., todos/doing)
Show full SKILL.md (153 more words)Show less

Classification Rules

StatusCriteriaAction
DONEFound commits that fully implement the todo's requirementsMove to $DONE
PARTIALSome related commits exist, but not all requirements metMove to $DOING
OPENNo related commits foundStay in $BACKLOG

Workflow

Step 1: Gather file list

List all .md files in $BACKLOG. If empty, tell the user and stop.

Step 2: Spawn sonnet subagent for analysis

Spawn a single sonnet subagent (model: "sonnet") with this prompt:

Read each todo file in {$BACKLOG} and determine its implementation status
by searching git history. For each file:

1. Read the file to understand what the task requires
2. Extract 3-5 search keywords from the title and content
3. Run `git log --oneline --all --grep="keyword"` for each keyword
4. If commits are found, read the commit messages to judge completeness
5. Classify as DONE / PARTIAL / OPEN

Files to check:
[list of file paths]

Report a markdown table:
| File | Status | Evidence |
|------|--------|----------|
| filename.md | DONE/PARTIAL/OPEN | commit hash + message, or "no related commits" |

Be conservative — only mark DONE if the commits clearly cover the full scope
described in the todo. If unsure, mark PARTIAL.
Step 3: Present results and confirm

Show the subagent's table to the user. Ask for confirmation before moving files. The user may override individual classifications.

Step 4: Move files

After confirmation:

  • DONE items → $DONE
  • PARTIAL items → $DOING
  • OPEN items → no action

Create target directories if they don't exist.

Report the final state:

todos/
├── backlog/   (N files remaining)
├── doing/     (N files)
├── done/      (N files)
└── later/     (N files)

Important

  • Never delete todo files — only move them
  • Always confirm with user before moving
  • The subagent does research only — it must not modify or delete any files

© hanamizuki, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/solopreneur/todos-cleanup of hanamizuki/solopreneur.

Open the folder on GitHubat commit f43f001

Compare with similar skills

Todos Cleanup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Todos Cleanup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Todos Cleanup this skillhanamizuki/solopreneur152—~1.5kAutomated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Migrate Internal Package into GhostTryGhost/Ghost56k—~3.8kAutomated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Contextual Commit Messagesyamadashy/repomix29k1 repos~2.7kAutomated safety check: PassMIT

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Moves a package from another TryGhost repository into Ghost as an internal workspace package while keeping its Git history, with checkpoints for the steps that need an administrator.

    56k GitHub stars~3.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed
  • Writes Conventional Commits whose bodies carry action lines recording the intent, decisions and constraints behind a change, not only what changed.

    29k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed
  • Git Merge Conflict Resolver

    tailcallhq/forgecode

    Resolves Git merge conflicts with a plan-first workflow that keeps both sides' intent, regenerates lock files and backs up deleted-but-modified files.

    7.6k GitHub starsUsed in 1 repo~4.5k tokens
    DevelopmentAuto-check passed

More from hanamizuki/solopreneur

All 31 skills in this repo
  • Preview

    hanamizuki/solopreneur

    Create an interactive HTML preview of any proposal, plan, idea, doc, brief, or spec and land it in the browsable local Preview Library by default (opens under file:// with a catalog sidebar and…

    152 GitHub stars~5.2k tokensUpdated 14 days ago
    Auto-check passed
  • iOS Patterns

    hanamizuki/solopreneur

    A skill your agent uses when building iOS/macOS apps with SwiftUI — covers localization (String Catalogs), date/time formatting, JSON date decoding, Previews, state management, sheet/navigation…

    152 GitHub stars~2.3k tokensUpdated 14 days ago
    Auto-check: notes
  • Linkedin Growth

    hanamizuki/solopreneur

    LinkedIn organic growth consultant — diagnoses profiles, discusses goals, and co-creates a personalized 90-day growth plan.

    152 GitHub stars~3.7k tokensUpdated 14 days ago
    Auto-check passed
  • Perspective

    hanamizuki/solopreneur

    Switch perspectives to think through problems using the mental models of ten iconic thinkers: Elon Musk, Richard Feynman, Charlie Munger, Naval Ravikant, Steve Jobs, Nassim Taleb, Ilya Sutskever…

    152 GitHub stars~971 tokensUpdated 14 days ago
    Auto-check passed
  • Slide Design

    hanamizuki/solopreneur

    Create brand-aware presentations using frontend-slides or reveal.js.

    152 GitHub stars~3.9k tokensUpdated 14 days ago
    Auto-check passed
  • X Growth

    hanamizuki/solopreneur

    X/Twitter growth consultant — diagnoses profiles, discusses goals, and co-creates a personalized growth plan.

    152 GitHub stars~3.8k tokensUpdated 14 days ago
    Auto-check passed

Categories

Questions about Todos Cleanup

What does Todos Cleanup do?

Batch cleanup of backlog todos — checks which items are already completed or partially done by searching git history, then moves them to done/ or doing/. Todos Cleanup is an agent skill from hanamizuki/solopreneur. Batch cleanup of backlog todos — checks which items are already completed or partially done by searching git history, then moves them to done/ or doing/.

When should I use Todos Cleanup?

Todos Cleanup fits situations like: the user says cleanup todos; clean up backlog; check todos status; wants to classify backlog items based on actual implementation status.

How do I install Todos Cleanup in Claude Code?

Run `npx skills add hanamizuki/solopreneur --skill todos-cleanup -a claude-code`. Or copy the skill folder (skills/solopreneur/todos-cleanup in hanamizuki/solopreneur) into .claude/skills/todos-cleanup in your project. Claude Code loads it when a task matches its description.

How do I install Todos Cleanup in Codex?

Run `npx skills add hanamizuki/solopreneur --skill todos-cleanup -a codex`. Or copy the skill folder (skills/solopreneur/todos-cleanup in hanamizuki/solopreneur) into .agents/skills/todos-cleanup in your project. Codex loads it when a task matches its description.

Can I use Todos Cleanup in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hanamizuki/solopreneur --skill todos-cleanup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/todos-cleanup, .gemini/skills/todos-cleanup, .github/skills/todos-cleanup and .opencode/skills/todos-cleanup in your project.

What does Todos Cleanup need to run?

SKILL.md names no scripts, command-line tools or credentials: Todos Cleanup is instructions for the agent only.

Does Todos Cleanup access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Todos Cleanup safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Todos Cleanup use?

Todos Cleanup is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Todos Cleanup use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Todos Cleanup?

Skills that share tags, products or a category with Todos Cleanup: Finishing a Development Branch (obra/superpowers, 297k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars), Migrate Internal Package into Ghost (TryGhost/Ghost, 56k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Todos Cleanup?

hanamizuki (a GitHub user) maintains it in hanamizuki/solopreneur, which has 152 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on September 26, 2026.

Source: hanamizuki/solopreneur on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.