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 skills add paulpreibisch/AgentVibes --skill bmad-distillatorgit clone --depth 1 https://github.com/paulpreibisch/AgentVibesWrote 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/paulpreibisch/agentvibes/bmad-distillator)<a href="https://agentmods.dev/skills/paulpreibisch/agentvibes/bmad-distillator"><img src="https://agentmods.dev/badge/skills/paulpreibisch/agentvibes/bmad-distillator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/paulpreibisch/agentvibes/bmad-distillator"><img src="https://agentmods.dev/badge/skills/paulpreibisch/agentvibes/bmad-distillator.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00035 | $0.02061 |
| Opus 5 | $0.00017 | $0.01030 |
| Sonnet 5 | $0.00007 | $0.00412 |
| Haiku 4.5 | $0.00003 | $0.00206 |
Grade A, and why
bmad-distillator 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 12d 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.
This is a copy
100% identical to bmad-distillator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distillator: A Document Distillation Engine
Overview
This skill produces hyper-compressed, token-efficient documents (distillates) from any set of source documents. A distillate preserves every fact, decision, constraint, and relationship from the sources while stripping all overhead that humans need and LLMs don't. Act as an information extraction and compression specialist. The output is a single dense document (or semantically-split set) that a downstream LLM workflow can consume as sole context input without information loss.
This is a compression task, not a summarization task. Summaries are lossy. Distillates are lossless compression optimized for LLM consumption.
On Activation
-
Validate inputs. The caller must provide:
- source_documents (required) — One or more file paths, folder paths, or glob patterns to distill
- downstream_consumer (optional) — What workflow/agent consumes this distillate (e.g., "PRD creation", "architecture design"). When provided, use it to judge signal vs noise. When omitted, preserve everything.
- token_budget (optional) — Approximate target size. When provided and the distillate would exceed it, trigger semantic splitting.
- output_path (optional) — Where to save. When omitted, save adjacent to the primary source document with
-distillate.mdsuffix. - --validate (flag) — Run round-trip reconstruction test after producing the distillate.
-
Route — proceed to Stage 1.
Stages
| # | Stage | Purpose |
|---|---|---|
| 1 | Analyze | Run analysis script, determine routing and splitting |
| 2 | Compress | Spawn compressor agent(s) to produce the distillate |
| 3 | Verify & Output | Completeness check, format check, save output |
| 4 | Round-Trip Validate | (--validate only) Reconstruct and diff against originals |
Stage 1: Analyze
Run scripts/analyze_sources.py --help then run it with the source paths. Use its routing recommendation and grouping output to drive Stage 2. Do NOT read the source documents yourself.
What ships with it
7 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.
- agents/distillate-compressor.md 4.8 KB
- agents/round-trip-reconstructor.md 2.7 KB
- resources/compression-rules.md 2.6 KB
- resources/distillate-format-reference.md 12 KB
- resources/splitting-strategy.md 3.3 KB
- scripts/analyze_sources.py 9.7 KB runs code
- scripts/tests/test_analyze_sources.py 7.5 KB runs code
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.
- 12d ago First seen · 177 lines · 35 tokens per session scan A 756ee0706ff6
bmad-distillator is a skill published in the GitHub repository paulpreibisch/AgentVibes (153 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 2,061 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to bmad-distillator, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
liteparse
Parse documents into LLM-ready content entirely on the local machine — PDF / DOCX / XLSX / PPTX / images → Markdown, structured JSON (with bounding boxes), or page screenshots, via the lit CLI. No cloud, no LLM, works offline. Use whenever the user attaches or points to a document that must be read before reasoning…
ingest
Turn external URLs and documents into LLM-ready content — load + cache web pages (HQCC compression) and OCR PDFs/images to Markdown. Use whenever the user gives a URL, asks you to read a webpage, or attaches a PDF/scan that needs to be parsed before reasoning. Executes via the cloud load, cloud search, and cloud parse…
video-timeline
Turn a final TTS audio track (with its timed transcript) into an editable story timeline (xlsx) for a human to fill with images, slides, and video clips. Audits the audio against timing best practices first, then maps each finding to a visual offset, and QA-scores the timeline objectively. Use when a finished…
transcript-to-pdf
Convert a GuideAnts / Code-Executor markdown conversation transcript into a styled, print-ready PDF with a cover page, role-badged turns, full tool-call inputs (heredoc-aware) and highlighted code. Use when the user wants to export, archive, or share a conversation log as a polished PDF document.
render-html
Render an artifact (or in-context material) as a bespoke, self-contained HTML file for one-shot human consumption. Writes to ephemeral scratch under $TMPDIR — these are consumption artifacts, not source, and nothing under .oh/ persists them. TRIGGER when: asked to render HTML, generate an HTML report, visualize an…
crw-parse
Parse a local or remote FILE (PDF) into markdown or structured JSON with fastCRW. Use when the source is a file on disk — "parse this PDF", "extract text from this document", "read this report", "convert PDF to markdown". Routing rule: URL → use crw-scrape; file on disk → use crw-parse. Step 5 of the crw workflow…