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-explainnpx skills add Juliocbm/beacon-docs --skill beacon-explaingit 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-explain)<a href="https://agentmods.dev/skills/juliocbm/beacon-docs/beacon-explain"><img src="https://agentmods.dev/badge/skills/juliocbm/beacon-docs/beacon-explain.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 | $0.00062 | $0.01810 |
| Opus 5 | $0.00031 | $0.00905 |
| Sonnet 5 | $0.00012 | $0.00362 |
| Haiku 4.5 | $0.00006 | $0.00181 |
Grade A, and why
beacon-explain 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 3d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/beacon:beacon-explain <term>
Renders the verbose explanation for a Beacon lint rule, doctor check, or plugin-contributed item. The CLI is the source of truth — this skill is a thin wrapper that picks the right CLI subcommand and presents the output faithfully.
The faithful-rendering rule (the most important rule)
Render the CLI's --explain output verbatim in a code block. Do NOT paraphrase, summarize, reshape, or add commentary.
The user invoked --explain. That word is the spec: they want the explanation, not your remix of it. Your training knowledge about kebab-case naming, ADR conventions, or doctor patterns is almost certainly less precise than what the CLI maintainer wrote into the rule's summary/why/fix fields.
✅ CORRECT response shape:
"Here's `beacon lint --explain kebab-case`:"
[verbatim CLI output, ~30 lines]
❌ WRONG response shapes:
- "The kebab-case rule means filenames must be lowercase..." (paraphrase)
- "**What it checks:** ... **Why:** ... **Fix:** ..." (reshape)
- "This rule is common because URLs are case-sensitive..." (commentary from training)
The user can ALWAYS ask for a summary afterward ("summarize that in 2 lines") — give them the raw first, summarize only on request.
Decision tree
User invoked /beacon:beacon-explain <args>?
│
├─ <args> is empty → ALL-CATALOG mode (see below)
│
└─ <args> has a term →
│
├─ Term obviously names a lint rule (suffix-location, kebab-case, etc.) → lint first
├─ Term obviously names a doctor check (stale-plans, proposed-adrs, etc.) → doctor first
└─ Ambiguous / unknown → PARALLEL both in one message
Pattern A — Term provided (the common case)
Run both beacon lint --explain <term> and beacon doctor --explain <term> in parallel (single message with two Bash tool calls). They're both read-only, both cheap, and parallel dispatch eliminates the wasted turn of sequential lint-then-doctor.
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.
- 3d ago First seen · 132 lines · 62 tokens per session scan A 4149decfe03b
beacon-explain is a skill published in the GitHub repository Juliocbm/beacon-docs (6 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 1,810 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…