loop-task

A workflow for implementation or bug-fix tasks that need a checkable result, using a written rubric and an independent verification cycle.

In plain words
What is it for?
Use it for substantial implementation or documentation changes that need rubric-based review and separate verification; it is not intended for simple questions or one-line fixes.
Why use it?
It adds a structured way to judge whether non-trivial code or documentation work meets its requirements before calling it finished.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/hiphapis/loopcraft/loop-task
Any agent
npx skills add hiphapis/loopcraft --skill loop-task
Clone the repo
git clone --depth 1 https://github.com/hiphapis/loopcraft

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,077 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00045 $0.01077
Opus 5 $0.00023 $0.00539
Sonnet 5 $0.00009 $0.00215
Haiku 4.5 $0.00005 $0.00108

Measured yesterday against content hash 2892c94f0240, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loop-task 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 yesterday.

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.

skills/loop-task/SKILL.md · 73 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. yesterday First seen · 73 lines · 45 tokens per session scan A 2892c94f0240

Subscribe to this mod's changes

loop-task is a skill published in the GitHub repository hiphapis/loopcraft (3 stars, last pushed 1mo ago), with no licence file. It adds 45 tokens to every session and 1,077 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

agent-recall

Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…

Goldentrii/AgentRecall-X · 157 tokens

fable-harness

Use when installing or updating a project-local Fable Harness for Codex, Claude Code, or compatible agent workflows; when a workspace needs AGENTS.md or CLAUDE.md boot instructions, .codex/.claude/.agents templates, decision traces, semantic notes, native loop governance, loop state, event logs, checklist evidence…

AAO-SH/fable-harness · 87 tokens

github-deep-review

GitHub deep review: bugs, PRs, best fix, stale-or-real, read code first.

sublimecoder/aios · 26 tokens

one-password

1Password/op: service-account first, targeted secret read/store/inject, tmux.

sublimecoder/aios · 21 tokens

obsidian-note-expert

Obsidian Knowledge Architect based on Progressive Summarization. Generates three-layer structure: Index -> Summary -> Detail. Always appends, never overwrites.

LeoLB-Wang/pensieve-obsidian-skill · 37 tokens

memory-loop

Update project memory after completing a task, making a key decision, discovering a gotcha, or changing active goals. Use this skill at the end of any meaningful unit of work to write structured entries into .claude/memory/MEMORY.md following the project schema. Also use when the user asks to save memory, update…

yucai0302/memory-loop · 76 tokens