oac-approach

oac-approach is a skill for Claude Code from darrenhinde/OpenAgentsControl. It costs 32 tokens per session (901 once invoked), scanned A, original, MIT.

A planning tool used before implementation begins. It examines the request and project context, then proposes a short plan for the user to approve before code is written.

In plain words
What is it for?
Use it when starting a coding task that needs alignment on scope, framework, database, or project conventions. It can discover relevant project guidance and include it in the proposed plan.
Why use it?
It reduces misunderstandings and prevents implementation from starting without the needed project details. It asks targeted questions only when the request or context leaves an important choice unclear.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the oac plugin — 12 skills, 6 commands, 7 agents, 1 hook shipped together

Good fit Use it when starting a coding task that needs alignment on scope, framework, database, or project conventions. It can discover relevant project guidance and include it in the proposed plan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/darrenhinde/openagentscontrol/oac-approach
About the project

OpenAgents Control is a framework that adds plan-first, approval-based coding workflows to OpenCode, an AI coding framework. Developers and teams use it to make agents follow shared coding patterns, work across several programming languages, and validate changes through testing and review. The catalogue includes its agents, skills, commands, plugin, and hook.

darrenhinde/OpenAgentsControl · 4,826 stars · on GitHub

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 darrenhinde/OpenAgentsControl --skill oac-approach
Clone the repo
git clone --depth 1 https://github.com/darrenhinde/OpenAgentsControl

Made for: Claude Code.

Or install oac, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 7 agents, 1 hook.

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 oac-approach

README.md
[![agentmods](https://agentmods.dev/badge/skills/darrenhinde/openagentscontrol/oac-approach.svg)](https://agentmods.dev/skills/darrenhinde/openagentscontrol/oac-approach)
Your own site
<a href="https://agentmods.dev/skills/darrenhinde/openagentscontrol/oac-approach"><img src="https://agentmods.dev/badge/skills/darrenhinde/openagentscontrol/oac-approach.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 901 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00032 $0.00901
Opus 5 $0.00016 $0.00451
Sonnet 5 $0.00006 $0.00180
Haiku 4.5 $0.00003 $0.00090

Measured 8d ago against content hash 217bdbbe4cb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

oac-approach 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.

plugins/claude-code/skills/oac-approach/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.

Plan Before You Code

Overview

Understand the request, discover relevant context, propose a concise plan, get approval. Keep it fast — the goal is alignment, not a design workshop.

The Process

Step 1: Understand the Request

Read the user's message. You already have the "what" — don't ask a series of questions up front. Only ask clarifying questions if:

  • The request is genuinely ambiguous (two different valid interpretations)
  • You discover during context check that key details are missing (e.g. which framework, which database)

In those cases, ask the specific questions you need — not a blanket "tell me more". Be explicit about what you need and why.

Step 2: Discover Context

Invoke oac:context-discovery with the task topic to find relevant project standards and patterns.

If context-discovery reports no context installed: proceed anyway — note it as "none" in the proposal and include the context hint (see Step 4). Do not pause or ask the user before proposing.

If context found: note the key files returned — reference them in your proposal.

Step 3: Ask Clarifying Questions (if needed)

After reviewing the context and the request, if there are still gaps that would significantly change the approach, ask them now — explicitly and concisely:

Before I propose an approach, I need a couple of details:

1. {specific question} — because {why it matters to the approach}
2. {specific question} — because {why it matters to the approach}

Keep it to the minimum needed. If you can make a reasonable assumption, state it in the proposal instead of asking.

Step 4: Propose

Present a lightweight plan. Short — not a full spec:

## Proposed Approach

**What**: {1-2 sentence description of what we're building/changing}
**How**: {brief description of approach — key decisions only}
**Assumptions**: {any assumptions made where questions weren't asked}
**Files**: {list of files to create or modify}
**Context loaded**: {key standards files found, or "none — using general best practices"}
**External docs needed**: {any library docs to fetch first, or "none"}

Approve or let me know what to adjust.

Read the full file on GitHub · 96 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 · 96 lines · 32 tokens per session scan A 217bdbbe4cb7

Subscribe to this mod's changes

oac-approach is a skill published in the GitHub repository darrenhinde/OpenAgentsControl (4,826 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 901 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