beacon-doctor

beacon-doctor is a skill for Claude Code from Juliocbm/beacon-docs. It costs 57 tokens per session (2,332 once invoked), scanned A, original, MIT.

An explicitly invoked command that runs Beacon's documentation health check and explains each finding.

In plain words
What is it for?
It helps review stale plans, unresolved decision records, and other documentation issues, then proposes actions for your confirmation.
Why use it?
It turns a list of technical checks into proposed next steps while keeping potentially destructive changes under your control.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the beacon plugin — 6 skills shipped together

Good fit It helps review stale plans, unresolved decision records, and other documentation issues, then proposes actions for your confirmation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/juliocbm/beacon-docs/beacon-doctor
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 Juliocbm/beacon-docs --skill beacon-doctor
Clone the repo
git clone --depth 1 https://github.com/Juliocbm/beacon-docs

Made for: Claude Code.

Or install beacon, the plugin that ships this one along with the rest of its 6 skills.

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 beacon-doctor

README.md
[![agentmods](https://agentmods.dev/badge/skills/juliocbm/beacon-docs/beacon-doctor.svg)](https://agentmods.dev/skills/juliocbm/beacon-docs/beacon-doctor)
Your own site
<a href="https://agentmods.dev/skills/juliocbm/beacon-docs/beacon-doctor"><img src="https://agentmods.dev/badge/skills/juliocbm/beacon-docs/beacon-doctor.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,332 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.
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 $0.00057 $0.02332
Opus 5 $0.00028 $0.01166
Sonnet 5 $0.00011 $0.00466
Haiku 4.5 $0.00006 $0.00233

Measured 8d ago against content hash ecd625c20154, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

beacon-doctor 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.

claude-plugin/skills/beacon-doctor/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/beacon:beacon-doctor

Runs beacon doctor, parses findings, proposes informed actions per finding, executes only on user confirmation. This skill turns the CLI's text output into an actionable workflow — but every destructive action requires explicit consent.

Core principle

Tools propose. Users decide. Agents execute.

The CLI's suggestion field on each finding is a hypothesis, not a command. Your job is to (a) parse what the doctor saw, (b) gather enough context to make the proposal informed, (c) ask for confirmation, (d) execute only on yes.

Mandate: always use --json

Run beacon doctor --json, never plain beacon doctor.

The text output is for humans reading their terminal. You need the structured array of {area, check, target?, observation, suggestion} objects to iterate over findings and propose specific actions. Parsing pretty-printed text with regex is fragile (CLI formatting can change); JSON is the stable contract.

beacon doctor --json

Reformatting JSON into human-readable output for your reply is trivial — that's what you're already good at. Rule: if a CLI offers --json and you need to act on the output, use it.

The all-clear case

When findings is empty (or []):

✔ All checks passed. (N areas inspected, M findings.)

Relay this and STOP. No padding. No "while we're here, want me to also run lint?" No preventive-measures suggestions. No offer to schedule periodic re-runs.

The user asked one question; they got the answer. The pull to add padding ("I should earn this turn") is a calibration bug, not a service to the user. A good doctor's visit ends with "you're fine, see you next year" — not invented follow-ups.

Per-finding flow (the normal case)

For each finding in findings[]:

Step 1 — Group by area, present concisely

Render findings grouped by area (activity / decisions / snapshots / balance). Each finding shows:

  • The target (file path or "project-wide")
  • The observation
  • The CLI's suggestion (verbatim, so the user sees what beacon thinks)

Read the full file on GitHub · 166 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 · 166 lines · 57 tokens per session scan A ecd625c20154

Subscribe to this mod's changes

beacon-doctor is a skill published in the GitHub repository Juliocbm/beacon-docs (6 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 2,332 once invoked, about $0.0003 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

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

baoyu-youtube-transcript

A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.

JimLiu/baoyu-skills · 107 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…

tw93/Waza · 78 tokens

overleaf-sync

A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.

wanshuiyin/Auto-claude-code-research-in-sleep · 97 tokens