auto-skill-loop

An automated workflow that coordinates several coding agents through planning, implementation, review, pull-request work, and other assigned steps. A pull request is a proposed code change submitted for review before it is merged.

In plain words
What is it for?
It helps run predefined multi-agent development loops, dispatch work to named roles, and repeatedly move tasks toward merged pull requests.
Why use it?
It removes the need for a person to manually coordinate each stage of a code change, but it requires explicit settings and permission to merge changes.

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/conn-castle/agent-layer/auto-skill-loop
Any agent
npx skills add conn-castle/agent-layer --skill auto-skill-loop
Clone the repo
git clone --depth 1 https://github.com/conn-castle/agent-layer

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 730 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.00730
Opus 5 $0.00009 $0.00365
Sonnet 5 $0.00003 $0.00146
Haiku 4.5 $0.00002 $0.00073

Measured 2d ago against content hash b546457fc2fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-skill-loop 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 2d 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.

internal/templates/skills/auto-skill-loop/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

auto-skill-loop

Inputs

Required:

  • a mode matching references/modes/<mode>.md
  • merge_authorization: standing authorization to merge under the gate below
  • operator, planner, one or more plan_reviewers, implementer, code_reviewer, pr_worker, and rote_worker dispatch targets

Optional:

  • loop_context: additional context for the orchestrator only
  • planner_context: additional context included only in step 1
  • ship_pr_context: additional context included only in step 2
  • operator_context: additional context included only in operator dispatches

Every input must be explicitly named in the skill invocation. Do not infer an unnamed input from unstructured text or from another input.

Rules

  • Use /dispatch-agent for every dispatch.
  • Act as the orchestrator. Delegate all work.
  • Build each dispatch prompt only from its specified prompt template.
  • When compacting, retain the original user inputs and this skill verbatim in addition to what you would normally retain.

Acting on the User's Behalf

This loop must run without human intervention. Each iteration is intended to result in a merged PR. For each loop that requires human input, dispatch operator in a fresh session. Use dispatch_continue for multiple invocations within a single loop. The first prompt should include the complete contents of references/human-guidance.md, followed by operator_context if provided, then the item requiring human input with all provided details verbatim.

If the operator determines that real human intervention is required, save the work to an appropriate remote branch for future handling, then check out the primary branch. Continue with another loop iteration. Do not block the loop waiting for human input.

Loop

  1. Dispatch planner with skill implement. Use the following as its prompt:
<complete contents of references/modes/<mode>.md>
<planner_context, if provided>

implementer: <implementer>
plan_reviewers: <plan_reviewers>
code_reviewer: <code_reviewer>

Return a self-contained `<implementation_input>` that states the actual task,
request, or spec you implemented and includes paths to plan artifacts if used.
This context will preserve the intended scope during later review.

Read the full file on GitHub · 96 lines

Files

What ships with it

7 files 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. 2d ago First seen · 96 lines · 17 tokens per session scan A b546457fc2fc

Subscribe to this mod's changes

auto-skill-loop is a skill published in the GitHub repository conn-castle/agent-layer (10 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 730 once invoked, about $0.0001 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