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.
npx agentmods add skills/juliocbm/beacon-docs/beacon-newnpx skills add Juliocbm/beacon-docs --skill beacon-newgit clone --depth 1 https://github.com/Juliocbm/beacon-docsWrote 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.
[](https://agentmods.dev/skills/juliocbm/beacon-docs/beacon-new)<a href="https://agentmods.dev/skills/juliocbm/beacon-docs/beacon-new"><img src="https://agentmods.dev/badge/skills/juliocbm/beacon-docs/beacon-new.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00050 | $0.03121 |
| Opus 5 | $0.00025 | $0.01561 |
| Sonnet 5 | $0.00010 | $0.00624 |
| Haiku 4.5 | $0.00005 | $0.00312 |
Grade A, and why
beacon-new 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/beacon:beacon-new <description>
Creates a new Beacon document by parsing a natural-language description into a beacon new <type> <slug> invocation. Handles type inference, slug extraction, add-on availability checks, and — critically — the explicit-path-vs-convention tension that produced the Option A architectural fix.
Core principle
Translate deterministically. Echo before execute. Ask only when genuinely ambiguous.
The user invoked a slash command — they expect action, not a confirmation gauntlet. But silent lossy translation (dropping words from the slug, picking the wrong type on ambiguous input, silently renaming explicit paths) is worse than one extra turn. The line: act on clear input, ask on ambiguous input, NEVER silently transform what the user typed.
Detection: description mode vs path mode
First, classify the $ARGUMENTS input:
| Input shape | Mode | Behavior |
|---|---|---|
Starts with docs/ or contains / |
Path mode | Treat as explicit path → check suffix vs convention → ask if mismatch |
| Free-text description, no path separator | Description mode | Parse type + slug, optionally ask, then execute |
Path mode is the Pattern 1 integration — the most important branch of this skill.
Path mode (the critical case)
User invoked: /beacon:beacon-new docs/plans/refactor-auth.md
The user typed a literal file path. They could have typed /beacon:beacon-new refactor-auth plan and gotten convention-compliant naming. Choosing a literal path is a SIGNAL of intent, not a hint to be helpful about.
The rule
An explicit literal path from the user is a stronger signal than a convention. When the path conflicts with the convention's suffix, ASK — do not silently apply the convention.
Specifically
- Extract the apparent type from the folder (
docs/plans/→ typeplan). - Compare the user's filename suffix against the convention's required suffix for that type:
- plans →
.plan.md - patterns →
.pattern.md - architecture →
.architecture.md - module →
.module.md - business →
.business.md - guide →
.guide.md - roadmap →
.roadmap.md - todo →
.todo.md - eval →
.eval.md(also requiresYYYY-MM-DD-prefix) - adr →
.md(withADR-NNN-prefix) - compliance →
.md(no suffix)
- plans →
- If suffix matches → run
beacon new <type> <slug>(slug extracted from filename minus suffix). Echo the command. - If suffix mismatches → ASK. Exactly this shape:
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.
- 5d ago First seen · 236 lines · 50 tokens per session scan A 2bb7ccef7025
beacon-new is a skill published in the GitHub repository Juliocbm/beacon-docs (6 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 3,121 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.
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…
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…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
gog-slides
Google Slides operations through gog.
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…