plan-automation-loop-skill

plan-automation-loop-skill is a skill for Claude Code, OpenCode from darellchua2/opencode-config-template. It costs 54 tokens per session (7,982 once invoked), scanned C, original, Apache-2.0.

An automated workflow for executing a PLAN.md file one phase at a time with checks between phases. It implements tasks, runs linting, builds, tests, and browser tests when relevant, then commits and pushes each completed phase.

In plain words
What is it for?
Use it to implement a development plan, add missing unit tests, run the verification sequence, retry bounded fixes, record traceability notes, and push completed phases.
Why use it?
It provides a repeatable end-to-end process that stops before advancing when the code does not pass its verification checks.

Skill for Claude CodeOpenCode

Written for Claude Code and OpenCode: $ARGUMENTS substitution, but also installed under .opencode/. Also seen: mentions subagents; mentions AGENTS.md; mentions OpenCode.

Good fit Use it to implement a development plan, add missing unit tests, run the verification sequence, retry bounded fixes, record traceability notes, and push completed phases.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/darellchua2/opencode-config-template/plan-automation-loop-skill
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 darellchua2/opencode-config-template --skill plan-automation-loop-skill
Clone the repo
git clone --depth 1 https://github.com/darellchua2/opencode-config-template

Made for: Claude Code, OpenCode.

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 plan-automation-loop-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/plan-automation-loop-skill.svg)](https://agentmods.dev/skills/darellchua2/opencode-config-template/plan-automation-loop-skill)
Your own site
<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/plan-automation-loop-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/plan-automation-loop-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,982 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00054 $0.07982
Opus 5 $0.00027 $0.03991
Sonnet 5 $0.00011 $0.01596
Haiku 4.5 $0.00005 $0.00798

Measured 4d ago against content hash cf13a61305a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

plan-automation-loop-skill scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Each phase = one iteration. Safety blocks `.env`, `node_modules/`, `rm -rf`, `git push --force`.
opencode_app/.opencode/skills/plan-automation-loop-skill/SKILL.md · 603 lines

How it starts

The opening of the file, as written. The whole thing — 603 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What I do

I run a fully-automated, phase-by-phase PLAN execution loop with a hard verification gate between phases. I am the "do the whole plan end-to-end, hands-off" skill:

  1. Resolve the plan from the /run-plan argument (explicit path/glob, or auto-detect from branch).
  2. Discover verification commands once (lint / build / test / e2e) from project manifests.
  3. For each phase, in order:
    • Implement every atomic step in the phase.
    • Ensure newly added code has unit tests (generate the missing ones first).
    • Run the verification gate: lint → build/typecheck → unit tests → Playwright e2e (frontend only).
    • Fix failures with bounded retries (max 3) — never push red.
    • On green: record a — Done: traceability line under each completed step (what was done + fixes applied + files), mark the phase checkbox [x], commit, push.
  4. Advance to the next phase. Repeat until all phases are done.
  5. Final validation against the plan's acceptance criteria.

I am the strict, push-per-phase sibling of plan-execution-skill. The difference: that skill delegates softly and updates progress; I enforce a gate, write missing tests, run e2e, leave a per-step traceability record, and commit+push every phase. I compose the existing skills rather than reimplementing them.

When to use me

Use this skill when:

  • The user drives a plan run through /goal (the primary path): e.g. /goal "load plan-automation-loop-skill and implement PLAN-*.md" --max-turns 40 --budget 400k. This wraps the skill in the plugin's hard guardrails (auto-resume, token/duration budgets, compaction-survival, evidence-gated completion).
  • The user types /run-plan PLAN-*.md (the fallback path — plain command, soft guardrails only, no plugin runtime hooks; use for short/watched runs).
  • The user says "fully implement the plan", "run the plan to completion", "automation loop".

Trigger phrases:

  • implement PLAN-*.md / fully implement PLAN / implement the plan
  • run plan to completion / automation loop
  • implement plan and commit per phase
  • "implement the plan with full automation"

Read the full file on GitHub · 603 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. 4d ago First seen · 603 lines · 54 tokens per session scan C cf13a61305a8

Subscribe to this mod's changes

plan-automation-loop-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 7,982 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.