authoring-adept-loops

authoring-adept-loops is a skill for Claude Code from itaywol/adeptability. It costs 60 tokens per session (1,030 once invoked), scanned A, original, MIT.

A guide for building scheduled agent workflows that discover tasks, assign them to agents, check the results independently, save their state, and run again later.

In plain words
What is it for?
Use it to create recurring triage or monitoring loops, such as a workflow that reviews continuous-integration failures, evaluates the work, stores progress, and reschedules itself.
Why use it?
It helps prevent automated routines from skipping verification, losing progress, or stopping because nobody remembered to run them.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to create recurring triage or monitoring loops, such as a workflow that reviews continuous-integration failures, evaluates the work, stores progress, and reschedules itself.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/itaywol/adeptability/authoring-adept-loops
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 itaywol/adeptability --skill authoring-adept-loops
Clone the repo
git clone --depth 1 https://github.com/itaywol/adeptability

Made for: Claude Code.

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 authoring-adept-loops

README.md
[![agentmods](https://agentmods.dev/badge/skills/itaywol/adeptability/authoring-adept-loops.svg)](https://agentmods.dev/skills/itaywol/adeptability/authoring-adept-loops)
Your own site
<a href="https://agentmods.dev/skills/itaywol/adeptability/authoring-adept-loops"><img src="https://agentmods.dev/badge/skills/itaywol/adeptability/authoring-adept-loops.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,030 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.
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 $0.00060 $0.01030
Opus 5 $0.00030 $0.00515
Sonnet 5 $0.00012 $0.00206
Haiku 4.5 $0.00006 $0.00103

Measured 8d ago against content hash 38512f5c0451, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

authoring-adept-loops 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 8d 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.

.adeptability/skills/authoring-adept-loops/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Composing a loop with adept

A loop is a system that prompts agents so a human doesn't have to: each turn it discovers work, hands off to an agent, verifies the result, persists state, and reschedules. Skip any move and the loop fails a predictable way — no verification is an agent nodding at itself; no persistence starts from scratch every morning; no schedule is a script someone forgets to run.

adept manages two of the six parts as canonical, synced resources — skills (discovery knowledge) and agents (the generator/evaluator pair). The rest (worktrees, connectors, memory files, schedules) belong to the harness and repo; this skill tells you how to wire them together.

Scaffold the composition

adept loop add ci-triage --workflow

creates:

  • skills/ci-triage/ — discovery skill (triage template: Read → Judge → Write → Hand off → Stop). activation: manual on purpose: the automation invokes it by name; it must not auto-fire in normal sessions.
  • agents/ci-triage-reviewer.md — evaluator agent (adversarial template: assume broken, act don't read, PASS/REJECT verdict).
  • .github/workflows/adept-loop-ci-triage.yml — cloud cron skeleton (only with --workflow); fill in the harness invocation + auth secret.

Then edit the scaffolds, adept agent check ci-triage-reviewer, adept sync.

The five moves, mapped

Move Where it lives adept's part
Discovery triage skill — what to read, how to judge noise vs. actionable adept skill add <id> --template triage
Handoff one git worktree per finding (claude --worktree, Codex background worktree) skill's "Hand off" section emits the task lines
Verification evaluator agent, different instructions (ideally different model) than the maker adept agent add <id> --template evaluator
Persistence ./state/<id>.md committed to the repo — the agent forgets, the repo does not skill's "Write" section owns it
Scheduling cloud cron (machine off, ≥1h interval) or local /loop/automations (machine on, minute-level) --workflow skeleton

Read the full file on GitHub · 78 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. 8d ago First seen · 78 lines · 60 tokens per session scan A 38512f5c0451

Subscribe to this mod's changes

authoring-adept-loops is a skill published in the GitHub repository itaywol/adeptability (9 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,030 once invoked, about $0.0003 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.