scan

scan is a skill for Claude Code, Codex from jacksenechal/scan-mcp. It costs 82 tokens per session (670 once invoked), scanned A, original, MIT.

A scanner-control skill that uses the scan-mcp server to capture documents, photos, receipts, and pages. It chooses a suitable connected scanner and default settings when the request has no special requirements.

In plain words
What is it for?
Use it for ordinary scans, photo scans, two-sided document stacks, and scans prepared for OCR, which means turning printed text into searchable digital text.
Why use it?
It removes repeated decisions about scanner selection and basic scan settings. You only need to specify details such as using a flatbed, scanning in colour, or capturing both sides when they matter.

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/jacksenechal/scan-mcp/scan
Any agent
npx skills add jacksenechal/scan-mcp --skill scan
Clone the repo
git clone --depth 1 https://github.com/jacksenechal/scan-mcp

Made for: Claude Code, Codex.

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 scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/jacksenechal/scan-mcp/scan.svg)](https://agentmods.dev/skills/jacksenechal/scan-mcp/scan)
Your own site
<a href="https://agentmods.dev/skills/jacksenechal/scan-mcp/scan"><img src="https://agentmods.dev/badge/skills/jacksenechal/scan-mcp/scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 670 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 $0.00082 $0.00670
Opus 5 $0.00041 $0.00335
Sonnet 5 $0.00016 $0.00134
Haiku 4.5 $0.00008 $0.00067

Measured 4d ago against content hash 923bb55cb095, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scan 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.

.claude/skills/scan/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scanner Control via scan-mcp

THE GOLDEN RULE

Trust the server defaults. When the user requests a scan without specific requirements:

  • Call start_scan_job({}) with NO parameters
  • Do NOT call list_devices unless the user explicitly asks for a specific scanner
  • Do NOT gather device capabilities "just in case"
  • Server auto-selects device, resolution (300dpi), color mode (Lineart), source (ADF Duplex → ADF → Flatbed)

Only override parameters when the user's intent clearly requires it.

Decision Tree

User request → Analyze intent:

1. Generic scan ("scan this", "scan document")
   → start_scan_job({}) immediately

2. User asks for specific scanner ("use the Epson")
   → list_devices, then start_scan_job({ device_id })

3. Document type needs special handling ("photo", "duplex")
   → Override only specific params needed

Common Overrides

User Intent Parameters
Generic scan {}
Photo scan { source: "Flatbed", color_mode: "Color", resolution_dpi: 600 }
Duplex stack { duplex: true }
OCR-optimized { color_mode: "Gray", resolution_dpi: 300 }

For more mappings, see EXAMPLES.md.

Standard Workflow

  1. Call start_scan_job(params) → receive { job_id, run_dir, state }
  2. Poll get_job_status({ job_id }) until state: "completed"
  3. Results in run_dir:
    • page_*.tiff (captured pages)
    • doc_*.tiff (assembled document)
    • manifest.json (metadata)
    • events.jsonl (event log)

Quick Troubleshooting

If scan fails:

  1. get_manifest({ job_id }) — check state and parameters
  2. get_events({ job_id }) — find error details in scanner_failed events
  3. Common fixes:
    • "No devices" → Ask user to check scanner power/connection
    • "Feeder jam" → Try { source: "Flatbed" }

For detailed troubleshooting, see TROUBLESHOOTING.md.

Reference Materials

  • TOOLS.md — Complete tool reference with all parameters
  • EXAMPLES.md — User intent → parameter mappings with reasoning
  • TROUBLESHOOTING.md — Detailed troubleshooting flows
  • CONFIG.md — Environment variables and configuration

Read the full file on GitHub · 71 lines

Files

What ships with it

4 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. 4d ago First seen · 71 lines · 0 tokens per session scan A 923bb55cb095

Subscribe to this mod's changes

scan is a skill published in the GitHub repository jacksenechal/scan-mcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 670 once invoked, about $0.0004 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.