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/stablebaseline/mcp/sb-authornpx skills add stablebaseline/mcp --skill sb-authorgit clone --depth 1 https://github.com/stablebaseline/mcpWrote 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/stablebaseline/mcp/sb-author)<a href="https://agentmods.dev/skills/stablebaseline/mcp/sb-author"><img src="https://agentmods.dev/badge/skills/stablebaseline/mcp/sb-author.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 | $0.00117 | $0.02158 |
| Opus 5 | $0.00059 | $0.01079 |
| Sonnet 5 | $0.00023 | $0.00432 |
| Haiku 4.5 | $0.00012 | $0.00216 |
Grade A, and why
sb-author 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stable Baseline: author documents
What this skill does
Creates and edits living documents in CDMD, a Markdown superset, and brings external files in as documents. Every change runs under the signed in user's own Stable Baseline identity and inherits their exact permissions.
IDs are never hardcoded. Resolve projectId, folderId and documentId at runtime
from listing calls made in this conversation.
Before you write anything
- Resolve scope.
listOrganisations,listWorkspaces,listProjects. If several workspaces or projects are accessible, ask which one. Never guess where a document should live. - Check whether it already exists. Run
listDocumentswith aquerybefore creating. Duplicating an existing document is a common and annoying failure. If a close match exists, show it and ask whether to edit that or create a new one. - Learn the format once per session. Call
getCdmdLanguageGuidebefore your first create or edit if you have not already. CDMD is not plain Markdown and guessing the block syntax produces broken documents.
Creating a document
createDocument requires projectId. It also accepts folderId, title, cdmd,
position and changeSummary.
- Always set a meaningful
title. - Always set
changeSummary. It appears in version history and is how colleagues understand what an agent did. - Place it deliberately. Ask for the folder if the project has several and the user has not
said.
createFolder,updateFolder,listFoldersandgetFolderHierarchymanage the tree;reorderDocumentsandreorderFolderschange display order.
Editing a document
editDocument is the preferred tool for targeted changes. It requires documentId and
supports two patch dialects that must not be mixed in one call.
Anchor patches, recommended. {oldText, newText, before?, after?}.
oldTextmust match the document byte for byte and be unique.- If it occurs more than once, expand
oldTextuntil unique, or addbeforeorafterwith the exact adjacent text. - A no-match returns nearby context. An ambiguous match returns the occurrence count. Read the error and fix the anchor rather than retrying blindly.
newText: ""deletes the anchored text.- Anchors do not drift and survive concurrent edits, so no fresh line numbers are needed.
- The
textfield inlistDocumentscontentMatchesis anchor-ready. Paste it straight in asoldText.
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 · 185 lines · 117 tokens per session scan A 6e0c21e46dce
sb-author is a skill published in the GitHub repository stablebaseline/mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 117 tokens to every session and 2,158 once invoked, about $0.0006 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…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
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.