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-workflownpx skills add Juliocbm/beacon-docs --skill beacon-workflowgit 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-workflow)<a href="https://agentmods.dev/skills/juliocbm/beacon-docs/beacon-workflow"><img src="https://agentmods.dev/badge/skills/juliocbm/beacon-docs/beacon-workflow.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 | $0.00061 | $0.02667 |
| Opus 5 | $0.00030 | $0.01333 |
| Sonnet 5 | $0.00012 | $0.00533 |
| Haiku 4.5 | $0.00006 | $0.00267 |
Grade A, and why
beacon-workflow 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beacon Workflow
Operational bridge between conversational signals and the beacon-docs CLI. Beacon's CLAUDE.md tells you what the rules are; this skill enforces how you follow them under conversational pressure where the natural pull is to skip the right action.
First action: detect the mode
Before responding to any documentation-related request, run:
test -f docs/_meta/beacon.config.json && echo ACTIVE || echo ADVISORY
| Result | Mode | Behavior |
|---|---|---|
ACTIVE |
Beacon installed | Use beacon new, beacon doctor, beacon archive. Never write doc files directly with Write tool. |
ADVISORY |
No Beacon | Describe conventions verbally; recommend npm install -g beacon-docs && beacon init if user shows interest. Don't run beacon commands — they'll fail. |
In ACTIVE mode, also read docs/_meta/beacon.config.json so you know which categories are enabled before suggesting beacon new <type>.
The discovery-first rule
Before any beacon new <type> call, search for existing related docs. This is the single check that prevents 90% of documentation drift.
ls docs/<category>/ # what's already there
grep -ri "<topic-keywords>" docs/ # any prior decisions on this?
If a relevant doc exists:
- If outdated/superseded → for ADRs, write a NEW ADR with
supersedes: <old-number>and update the old ADR'ssuperseded-by. For evals, create a new dated eval referencing the old. - If accurate → link to it. Don't duplicate.
- If partial → extend it (allowed for plans, patterns, architecture; NEVER for ADRs or evals).
Rationalization to reject: "Discovery feels like stalling, the user wants action." A grep takes 100ms. Creating a contradictory document costs days of cleanup later. The discovery step IS the action.
Conversational triggers → beacon commands
Map the user's signal to the command. Draft inline; don't ask permission to write.
| Signal | Command | Notes |
|---|---|---|
| "decidí X", "vamos con X", "X over Y", architecture/dependency choice | beacon new adr <slug> |
First: grep docs/adr/ for prior decisions on same topic. If found, frame as supersede. |
| 3+ distinct implementation steps agreed | beacon new plan <slug> |
Body uses - [ ] checkboxes; check off in same commit that completes each step. |
| "lo dejamos para después", "out of scope", "v0.5", "más adelante" | beacon new todo <slug> |
Single tool call, then continue. This takes 5 seconds, not 5 minutes. |
| Tag/release shipped, milestone reached | beacon new eval <slug>-retrospective |
Draft 10-line eval yourself from session context; offer for review. Don't wait for user input. |
| Same approach explained 2+ times across files/sessions | beacon new pattern <slug> |
Lives in reference/. |
| New module, layer, external dependency | Update or add doc in architecture/ |
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 · 192 lines · 61 tokens per session scan A 38af66a47aaf
beacon-workflow is a skill published in the GitHub repository Juliocbm/beacon-docs (6 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 2,667 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
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…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
file-forensics
Examine what a file claims about itself and what it actually contains — powered by Apache Tika. True content-based type detection (extensions lie), provenance claims (authors, dates, creating application), revision and tamper signals (PDF incremental updates, tracked changes, hidden slides, zip integrity), hidden and…