orc-clarify

orc-clarify is a skill for Claude Code, Codex from qGolem/orc. It costs 15 tokens per session (1,186 once invoked), scanned A, original, MIT.

A decision-making conversation between initial project discovery and detailed planning. It connects the user's goals with what the existing codebase can actually support.

In plain words
What is it for?
Use it to review project findings, resolve mismatches between the vision and current code, and record decisions for later phases.
Why use it?
It surfaces conflicts and unanswered choices so important decisions are made before implementation planning.

Skill for Claude CodeCodex

Part of the orc plugin — 29 skills, 27 agents shipped together

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/qgolem/orc/orc-clarify
Any agent
npx skills add qGolem/orc --skill orc-clarify
Clone the repo
git clone --depth 1 https://github.com/qGolem/orc

Made for: Claude Code, Codex.

Or install orc, the plugin that ships this one along with the rest of its 29 skills, 27 agents.

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 orc-clarify

README.md
[![agentmods](https://agentmods.dev/badge/skills/qgolem/orc/orc-clarify.svg)](https://agentmods.dev/skills/qgolem/orc/orc-clarify)
Your own site
<a href="https://agentmods.dev/skills/qgolem/orc/orc-clarify"><img src="https://agentmods.dev/badge/skills/qgolem/orc/orc-clarify.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,186 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 $0.00015 $0.01186
Opus 5 $0.00008 $0.00593
Sonnet 5 $0.00003 $0.00237
Haiku 4.5 $0.00002 $0.00119

Measured 4d ago against content hash 21cdc8d64f80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orc-clarify 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/orc-clarify/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orc Clarify

Dream extraction applied to technical reality. Surfaces questions that emerged from codebase discovery and gets decisions before planning.

Philosophy

You are a thinking partner, not a status reporter. Discovery found things. Now help the user decide what those findings mean for their vision.

Your role:

  • Surface conflicts between vision and codebase reality
  • Present findings as decision points, not information dumps
  • Challenge "whatever you think" responses—the user needs to own these decisions
  • Capture decisions in the right places for downstream phases

Not your role:

  • Making architectural decisions for the user
  • Dumping all findings without prioritizing
  • Skipping this step because "it seems straightforward"
  • Accepting vague answers to move faster

Input

  • $ARGUMENTS — Plan slug

Process

Step 1: Load Context

Read:

  • .claude/plans/$ARGUMENTS/PROJECT.md — user's vision
  • .claude/plans/$ARGUMENTS/STATE.md — codebase findings
  • .claude/plans/$ARGUMENTS/research/SUMMARY.md — domain research synthesis (if exists)

Step 2: Identify Decision Points

Scan for gaps between vision and codebase reality:

Pattern conflicts:

  • STATE.md found patterns that differ from what PROJECT.md describes
  • Existing conventions that the vision doesn't account for

Reuse opportunities:

  • Existing code that could be leveraged (user should decide if they want to)
  • Similar features already implemented (follow pattern or diverge?)

Discovered constraints:

  • Technical limitations not mentioned in the interview
  • Dependencies that affect the approach
  • Risk factors that need user awareness

Open questions:

  • Questions explicitly flagged in STATE.md
  • Ambiguities that would affect phase planning

Step 3: Prioritize Findings

Not all findings need discussion. Prioritize:

Must discuss:

  • Conflicts that would change the approach
  • Decisions that affect multiple phases
  • Risks rated High in STATE.md

Can skip:

  • Minor style/convention details (just follow existing)
  • Low-risk integration points
  • Things clearly answered in PROJECT.md

Read the full file on GitHub · 177 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 · 177 lines · 15 tokens per session scan A 21cdc8d64f80

Subscribe to this mod's changes

orc-clarify is a skill published in the GitHub repository qGolem/orc (5 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 1,186 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

new-skill

Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…

hyhmrright/brooks-lint · 145 tokens

status

Where is the work right now. Regenerates the projections and the kanban board from the journal and answers with the progress line, the agents still running, the open gates and the resume steps. Read-only. Use for /tyran:status or when asked what is going on.

jjanczur/tyran · 58 tokens

prompt-tuning

Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.

jjanczur/tyran · 58 tokens

brainstorm

Explores a codebase, researches the problem space, and produces an approved design specification before any code is written. Use when the user wants to create a new feature, add significant functionality, redesign a subsystem, or build something that touches multiple parts of the project.

greglas75/zuvo · 56 tokens

a11y-audit

Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…

greglas75/zuvo · 147 tokens

api-audit

API and endpoint integrity audit across 10 dimensions (D1-D10) plus optional contract stability (D11) and optional OWASP API Security Top 10 (D12: BOLA/BOPLA/BFLA, mass assignment, JWT alg-confusion, GraphQL introspection). Covers validation, payloads, pagination, errors, caching, HTTP semantics, waterfalls, rate…

greglas75/zuvo · 135 tokens