orc-scout

orc-scout is a skill for Claude Code from qGolem/orc. It costs 12 tokens per session (898 once invoked), scanned A, original, MIT.

A codebase discovery tool for one project phase. It examines the files named in a phase plan and the surrounding code that depends on them.

In plain words
What is it for?
Use it before implementation to map target files, their dependencies, related tests, and cross-phase connections.
Why use it?
It gives the implementation phase relevant context, including related files, imports, tests, and earlier phase work.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

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

Made for: Claude Code.

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-scout

README.md
[![agentmods](https://agentmods.dev/badge/skills/qgolem/orc/orc-scout.svg)](https://agentmods.dev/skills/qgolem/orc/orc-scout)
Your own site
<a href="https://agentmods.dev/skills/qgolem/orc/orc-scout"><img src="https://agentmods.dev/badge/skills/qgolem/orc/orc-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 898 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 5.1 $0.00012 $0.00898
Opus 5 $0.00006 $0.00449
Sonnet 5 $0.00002 $0.00180
Haiku 4.5 $0.00001 $0.00090

Measured 6d ago against content hash 03ef78985596, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

orc-scout 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 6d 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-scout/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orc Scout

Phase-scoped codebase discovery that runs forked (non-interactive). Explores files referenced in PLAN.md and their surrounding code. For phases > 1, reads prior phase artifacts for cross-phase awareness.

Input

  • $ARGUMENTS{slug} {phase-num} (e.g., my-feature 2)

Template

See templates/SCOUT.md for output format.

Process

Step 1: Parse Arguments and Locate Phase

slug = first word of $ARGUMENTS
phase_num = second word of $ARGUMENTS

Find phase directory:

Glob .claude/plans/{slug}/phases/0{phase_num}-*/PLAN.md

Read the matched PLAN.md.

Step 2: Extract Target Files

From PLAN.md, collect all target files:

  • files_modified from frontmatter
  • must_haves.artifacts paths
  • <files> sections from each task

Deduplicate into a single list.

Step 3: Analyze Each Target File

For each target file:

Existence & size:

Glob for the file path
Bash: wc -l {file}

Imports (what it depends on):

Grep: import.*from in the file

Imported by (what depends on it):

Grep: import.*{filename} across src/

Related tests:

Glob: **/{basename}.test.* and **/{basename}.spec.*

Dependency graph:

Bash: madge --depends {file}

Step 4: Analyze Target Directories

For each unique directory containing target files:

Bash: tree -L 2 -P '*.ts' {target-dir}

Step 5: Discover Conventions

From the target files and their neighbors, document:

  • Naming conventions (files, exports, variables)
  • Error handling patterns
  • Testing patterns (framework, mocking, location)
  • Import organization

Include file:line references for each convention.

Step 6: Cross-Phase Context (phase > 1 only)

If phase_num > 1, read prior phase artifacts:

Glob .claude/plans/{slug}/phases/0{prior}-*/PROGRESS-*.md  → Read each match
Glob .claude/plans/{slug}/phases/0{prior}-*/SUMMARY-*.md   → Read each match
Glob .claude/plans/{slug}/phases/0{prior}-*/IMPL-VERIFICATION.md  → Read if exists

Fallback: If PROGRESS-*.md not found, try reading PROGRESS.md (single-executor phases)
Fallback: If SUMMARY-*.md not found, try reading SUMMARY.md (single-executor phases)

Read the full file on GitHub · 138 lines

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. 6d ago First seen · 138 lines · 0 tokens per session scan A 03ef78985596

Subscribe to this mod's changes

orc-scout is a skill published in the GitHub repository qGolem/orc (5 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 898 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

recipe-front-review

Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.

shinpr/claude-code-workflows · 29 tokens

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

recipe-add-integration-tests

Add integration/E2E tests to existing codebase using Design Docs.

shinpr/claude-code-workflows · 19 tokens

llm-friendly-context

Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.

shinpr/claude-code-workflows · 52 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

write-article

Write high-quality articles from scratch using a 6-phase pipeline: deep STORM-inspired research with parallel agents, multi-perspective outline generation, section-by-section drafting with research grounding, adaptive anti-slop enforcement (hard/soft banned vocabulary per tone), cross-model adversarial review, and SEO…

greglas75/zuvo · 125 tokens