Agent skill

Timeboxed Iterating

by av in av/mi

Runs a task for a fixed duration by dispatching subagents in a loop, with the clock, not the agent, deciding when to stop.

No licenceAuto-check passedAgent Workflows

Install Timeboxed Iterating

skills CLI
$ npx skills add av/mi --skill timeboxed-iterating -a claude-code

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

GitHub CLI
$ gh skill install av/mi timeboxed-iterating --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/av/mi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/timeboxed-iterating .claude/skills/timeboxed-iterating && 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
timeboxed-iterating
GitHub stars
102
Token cost
~2.3k tokens
SKILL.md length
1,103 words
Files
2
Skills in repo
20
Repo updated
First seen
Licence
None found

At a glance

Runs a task for a fixed duration by dispatching subagents in a loop, with the clock, not the agent, deciding when to stop.

  • Works in 2 steps: Manage the clock — check time before… → Dispatch subagents — give them the goal,…
  • Working on a goal for a set number of hours, such as overnight
  • SKILL.md covers Your Role, The Iron Law, Inputs and The Process, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

You give the skill a goal and a duration, such as improving test coverage for 90 minutes or working overnight, which it reads as 8 hours. The main agent then acts only as an orchestrator: it records the start time with date +%s, computes the deadline, creates a progress file under /tmp, and from then on checks the clock before every dispatch.

Each subagent receives the goal and the progress file path, reads that file to learn what was already done, completes one meaningful unit of work, commits it and returns a structured summary of what was done and what high-impact work remains. The orchestrator makes no code changes, edits or analysis itself and has no authority to call the work finished early; it keeps dispatching until the deadline passes.

When your agent uses it

  • Working on a goal for a set number of hours, such as overnight
  • Letting subagents make repeated improvements with a hard stop at the deadline
  • Spreading a large cleanup or coverage task over many small commits

Example prompts

  • “Spend 90 minutes improving test coverage in the api package, using subagents.”
  • “Work on refactoring the legacy parser overnight, in timeboxed iterations.”
  • “Build out the spec for the export feature over the next three hours.”

Requirements

  • An agent that can dispatch subagents
  • A shell that can run the date command
  • A git repository for the subagents' commits

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Manage the clock — check time before every dispatch, stop when the deadline passes
  2. Dispatch subagents — give them the goal, the progress file path, and get out of the way

What it can do on your machine

Read from SKILL.md and the folder at commit 2bf50c9. 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 markdown and dot).

    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

Timeboxed Iterating loads about 2.3k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 1,103 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,103 words (~2,278 tokens).

“Run a task iteratively via subagents for a user-specified duration. The clock is the only authority on when to stop. You are not.”

— opening of SKILL.md by av
name
timeboxed-iterating

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in .agents/skills/timeboxed-iterating of av/mi.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit 2bf50c9

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in av/mi, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Timeboxed Iterating 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.

Timeboxed Iterating compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Timeboxed Iterating this skillav/mi102—~2.3kAutomated safety check: PassNone
Migrating Claude Agent SDK To Pydantic AIpydantic/pydantic-ai20k—~1.6kAutomated safety check: PassMIT
Cursor Orchestratecursor/plugins10k—~1.1kAutomated safety check: PassNone
Agent-Foreman Feature Runmylukin/agent-foreman250—~1.6kAutomated safety check: NotesNone
Spec-Driven Development v2LichAmnesia/lich-skills234—~3.1kAutomated safety check: PassMIT
Optimizeevo-hq/evo1.5k—~13kAutomated safety check: PassApache-2.0

Similar skills

  • Official

    Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness.

    20k GitHub stars~1.6k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Cursor Orchestrate

    cursor/plugins

    Official

    Splits a large goal into a tree of parallel Cursor cloud agents, with planners, workers and verifiers coordinated by a script and reporting through structured handoffs.

    10k GitHub stars~1.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Agent-Foreman Feature Run

    mylukin/agent-foreman

    Runs the agent-foreman task loop for one task by ID or unattended across every pending task, following next, implement, check, done for each one.

    250 GitHub stars~1.6k tokensUpdated 8 mo ago
    Agent WorkflowsAuto-check: notes
  • Spec-Driven Development v2

    LichAmnesia/lich-skills

    Organizes long-running agent work into a Project, Sprint and Task hierarchy with per-task state files, isolated worktrees, review loops and script-checked rules.

    234 GitHub stars~3.1k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed
  • Optimize

    evo-hq/evo

    Drive structured autoresearch iteration after evo:discover and the baseline commit.

    1.5k GitHub stars~13k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Babysitter Process Runner

    a5c-ai/babysitter

    Execute via @babysitter. Use this skill when asked to babysit a task, do anything that is structured process-driven (even a loop) or whenever it is called…

    1.8k GitHub starsUsed in 1 repo~726 tokens
    Agent WorkflowsAuto-check: notes
  • Writes plain-English integration test specs with verifiable steps and expectations, then runs each one through a subagent that reports pass or fail with logs.

    102 GitHub stars~908 tokensUpdated 11 days ago
    Auto-check passed
  • Anneal

    av/mi

    A skill your agent uses when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other…

    102 GitHub stars~3.8k tokensUpdated 11 days ago
    Auto-check passed
  • Scans a codebase to tag every fact as draft, spec or implemented based on what the code actually shows, adding missing facts and fixing or removing wrong ones.

    102 GitHub stars~2.8k tokensUpdated 11 days ago
    Auto-check passed
  • Implements every @spec fact from a project's fact sheet in code, tags each one @implemented once done, and reports exactly what is left if it cannot finish.

    102 GitHub stars~1.3k tokensUpdated 11 days ago
    Auto-check passed
  • Works with you to turn draft behavioral facts into precise, implementable spec facts, resolving vague labels, gaps and contradictions one at a time through discussion.

    102 GitHub stars~1.5k tokensUpdated 11 days ago
    Auto-check passed
  • Ideate

    av/mi

    Timeboxed ideation on a topic using propose-and-critique subagent pairs.

    102 GitHub stars~2.8k tokensUpdated 11 days ago
    Auto-check passed

Categories

Questions about Timeboxed Iterating

What does Timeboxed Iterating do?

Runs a task for a fixed duration by dispatching subagents in a loop, with the clock, not the agent, deciding when to stop. You give the skill a goal and a duration, such as improving test coverage for 90 minutes or working overnight, which it reads as 8 hours. The main agent then acts only as an orchestrator: it records the start time with date +%s, computes the deadline, creates a progress file under /tmp, and from then on checks the clock before every dispatch.

When should I use Timeboxed Iterating?

Timeboxed Iterating fits situations like: working on a goal for a set number of hours, such as overnight; letting subagents make repeated improvements with a hard stop at the deadline; spreading a large cleanup or coverage task over many small commits.

How do I install Timeboxed Iterating in Claude Code?

Run `npx skills add av/mi --skill timeboxed-iterating -a claude-code`. Or copy the skill folder (.agents/skills/timeboxed-iterating in av/mi) into .claude/skills/timeboxed-iterating in your project. Claude Code loads it when a task matches its description.

How do I install Timeboxed Iterating in Codex?

Run `npx skills add av/mi --skill timeboxed-iterating -a codex`. Or copy the skill folder (.agents/skills/timeboxed-iterating in av/mi) into .agents/skills/timeboxed-iterating in your project. Codex loads it when a task matches its description.

Can I use Timeboxed Iterating 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 av/mi --skill timeboxed-iterating -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/timeboxed-iterating, .gemini/skills/timeboxed-iterating, .github/skills/timeboxed-iterating and .opencode/skills/timeboxed-iterating in your project.

What does Timeboxed Iterating need to run?

SKILL.md names no scripts, command-line tools or credentials: Timeboxed Iterating is instructions for the agent only. Our summary lists: An agent that can dispatch subagents; A shell that can run the date command; A git repository for the subagents' commits.

Does Timeboxed Iterating 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 Timeboxed Iterating 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 Timeboxed Iterating use?

No licence was found for Timeboxed Iterating or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Timeboxed Iterating use?

About 2.3k tokens (SKILL.md is roughly 9.1k 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 Timeboxed Iterating?

Skills that share tags, products or a category with Timeboxed Iterating: Migrating Claude Agent SDK To Pydantic AI (pydantic/pydantic-ai, 20k stars), Cursor Orchestrate (cursor/plugins, 10k stars), Agent-Foreman Feature Run (mylukin/agent-foreman, 250 stars) and Spec-Driven Development v2 (LichAmnesia/lich-skills, 234 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Timeboxed Iterating?

av (a GitHub user) maintains it in av/mi, which has 102 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on September 26, 2026.

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