dale-loop-repo

dale-loop-repo is a skill for Codex from lubluniky/dale. It costs 30 tokens per session (347 once invoked), scanned A, original, MPL-2.0.

A recurring repository-maintenance workflow that checks issues, pull requests, continuous-integration results, dependencies, and project priorities, then assigns bounded engineering tasks to fresh agent runs.

In plain words
What is it for?
It is for monitoring a repository, selecting verifiable maintenance work, coordinating implementation and review, and tracking tasks through their checks and merge gates.
Why use it?
It keeps maintenance work moving across repeated check-ins while avoiding duplicate tasks and limiting risky or vague changes.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents; mentions Codex.

Good fit It is for monitoring a repository, selecting verifiable maintenance work, coordinating implementation and review, and tracking tasks through their checks and merge gates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lubluniky/dale/dale-loop-repo
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 lubluniky/dale --skill dale-loop-repo
Clone the repo
git clone --depth 1 https://github.com/lubluniky/dale

Made for: 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 dale-loop-repo

README.md
[![agentmods](https://agentmods.dev/badge/skills/lubluniky/dale/dale-loop-repo/github.svg)](https://agentmods.dev/skills/lubluniky/dale/dale-loop-repo)
Your own site
<a href="https://agentmods.dev/skills/lubluniky/dale/dale-loop-repo"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-loop-repo/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 dale-loop-repo

Your own site · 80×15
<a href="https://agentmods.dev/skills/lubluniky/dale/dale-loop-repo"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-loop-repo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 347 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 $0.00030 $0.00347
Opus 5 $0.00015 $0.00173
Sonnet 5 $0.00006 $0.00069
Haiku 4.5 $0.00003 $0.00035

Measured 4d ago against content hash 2a86e89c88b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dale-loop-repo 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 4d 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.

skills/dale-loop-repo/SKILL.md · 36 lines

What it actually says

Dale Loop Repo

Use a product automation for the requested cadence. Record priority sources, allowed actions, merge authority, direct checks, and terminal condition. On each wake inspect current repository state, open work, and CI before choosing an action. Prefer already-started or blocking work to inventing new work.

Select bounded work with observable acceptance criteria. Delegate independent parts to subagents during the run, inheriting model settings. Give each an exclusive scope or read-only role and forbid further delegation. Use explicit worktree isolation for concurrent writers when necessary. Separate Codex tasks require an explicit user request; unavailable task tools do not block local work.

Persist source/PR identities, actions, findings, and next condition so a future wake can resume without a living worker. Prevent duplicate dispatch against unchanged state. Verify reports against live systems and respect publication and merge authority. Do not expand routine maintenance into unrelated product, security, deployment, or destructive changes.

Notify only after meaningful action, failure, completion, or required input. Remain quiet when unchanged. Disable scheduled work at its terminal condition; archive the user task only when asked. Back off and report repeated blockers.

Cancellation and changed scope

On cancellation or revoked scope, interrupt affected workers immediately before other work, invalidate pending outputs, and preserve existing changes. Update or disable related scheduled work only within the user's cancellation scope. For a correction, stop conflicting work first, then send the revised contract; accept subsequent results only against the current request and artifact state.

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. 4d ago Changed · +14 lines · -34 tokens per session 2a86e89c88b8
  2. 12d ago First seen · 22 lines · 64 tokens per session scan A baf7fe03add2

Subscribe to this mod's changes

dale-loop-repo is a skill published in the GitHub repository lubluniky/dale (51 stars, last pushed 6d ago), licensed MPL-2.0. It adds 30 tokens to every session and 347 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 2026-08-30.

Related

Other skills, from other repositories