harbor: Skill for Claude Code

.agents/skills/timeboxed-iterating/SKILL.md

timeboxed-iterating is a skill for Claude Code, Codex from av/harbor. It costs 32 tokens per session (2,152 once invoked), scanned A, original, Apache-2.0.

A workflow for having several agents repeatedly work on a task until a user-set time limit ends. One coordinator tracks the clock and sends work to subagents.

In plain words
What is it for?
Use it for time-limited tasks such as improving tests, refining a specification, or repeatedly reviewing and improving project work.
Why use it?
It keeps iterative work running for the requested duration and prevents the coordinator from deciding early that the task is finished.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is av/harbor's own configuration. It tells Claude Code and Codex how to work on harbor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything harbor configures →

About the project

av/harbor is a command-line tool and companion app that uses Docker Compose to start a connected local stack of language-model backends, user interfaces, and supporting AI services. People use it to run services such as Ollama, llama.cpp, vLLM, Open WebUI, search, voice, and image-generation tools without configuring their connections manually, while the catalogue provides agent workflows for operating Harbor.

av/harbor · 3,263 stars · on GitHub · discord.gg

Reuse

Borrowing it

Nothing to install: this file belongs to av/harbor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/av/harbor/main/.agents/skills/timeboxed-iterating/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/av/harbor

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 timeboxed-iterating

README.md
[![agentmods](https://agentmods.dev/badge/skills/av/harbor/timeboxed-iterating/github.svg)](https://agentmods.dev/skills/av/harbor/timeboxed-iterating)
Your own site
<a href="https://agentmods.dev/skills/av/harbor/timeboxed-iterating"><img src="https://agentmods.dev/badge/skills/av/harbor/timeboxed-iterating/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 timeboxed-iterating

Your own site · 80×15
<a href="https://agentmods.dev/skills/av/harbor/timeboxed-iterating"><img src="https://agentmods.dev/badge/skills/av/harbor/timeboxed-iterating.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,152 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
SkillSpector: 2 findings, up to low

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • low Excessive Agency · line 151
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
  • low Excessive Agency · line 183
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
How audits are shown
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 $0.00032 $0.02152
Opus 5.5 $0.00013 $0.00861
Sonnet 5.5 $0.00006 $0.00430
Haiku 4.5 $0.00003 $0.00215

Measured 2mo ago against content hash d32cedd064ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

timeboxed-iterating 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.

.agents/skills/timeboxed-iterating/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Timeboxed Iterating

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

Your Role

You are the orchestrator. You do exactly two things:

  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

You do NOT do any actual work. No code changes, no file edits, no exploration, no analysis, no "quick fixes." All productive work happens inside subagents. Your context is reserved exclusively for the dispatch loop. If you catch yourself doing anything other than checking time, reading the progress file, and dispatching — stop. That work belongs in a subagent.

The Iron Law

YOU DO NOT DECIDE WHEN THE WORK IS DONE. THE CLOCK DECIDES.

Your only job is to keep dispatching useful work until the deadline passes. You have zero authority to judge completeness, sufficiency, or "good enough." The user gave you a duration. You use all of it.

Inputs

The user provides two things:

  1. Goal — what to do (e.g., "improve test coverage", "refactor AI slop", "build out the spec")
  2. Duration — how long to do it (e.g., "4 hours", "overnight", "90 minutes")

If the duration is vague ("overnight"), interpret it as 8 hours. If truly ambiguous, ask once.

The Process

digraph timeboxed {
    rankdir=TB;
    node [shape=box];

    start [label="Record start time\nCompute deadline" shape=doublecircle];
    init [label="Create progress file\nin /tmp"];
    check [label="Check current time\nagainst deadline" shape=diamond];
    read_log [label="Read progress file\nfor orchestrator context"];
    dispatch [label="Dispatch subagent\nwith goal + progress file path"];
    update [label="Update progress file\nwith iteration results"];
    summary [label="Write final summary\nto progress file" shape=doublecircle];

    start -> init -> check;
    check -> read_log [label="time remains"];
    check -> summary [label="deadline passed"];
    read_log -> dispatch;
    dispatch -> update;
    update -> check;
}

Read the full file on GitHub · 193 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 193 lines · 32 tokens per session scan A d32cedd064ec

Subscribe to this mod's changes

timeboxed-iterating is a skill published in the GitHub repository av/harbor (3,263 stars, last pushed 6d ago), licensed Apache-2.0. It adds 32 tokens to every session and 2,152 once invoked, about $0.0001 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 2026-08-30.

Related

timeboxed-iterating compared with skills from other repositories

timeboxed-iterating next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
timeboxed-iteratingav/harborSkill3.3k6d agoApache-2.0A32Claude Code, Codex
hugging-face-tool-buildersynthetic-sciences/openscienceSkill4.3k2d agoApache-2.0A67Claude Code, Codex
agent-builderchandrudp29/skillhubSkill144mo agoMITA42Claude Code, Codex
synapsedinglebear-ai/synapseSkill24d agoAGPL-3.0A67Claude Code
docker-essentialsasgarovf/locusaiSkill238mo agoMITA35Claude Code
docker-managementfurkangonel/cowranglerSkill11mo agoMITC16Claude Code, Codex
clinicaltrials-databasesynthetic-sciences/openscienceSkill4.3k2d agoApache-2.0A47Claude Code, Codex