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/evolplus/talos/ba-mode-single-docnpx skills add evolplus/talos --skill ba-mode-single-docgit clone --depth 1 https://github.com/evolplus/talosWrote 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/evolplus/talos/ba-mode-single-doc)<a href="https://agentmods.dev/skills/evolplus/talos/ba-mode-single-doc"><img src="https://agentmods.dev/badge/skills/evolplus/talos/ba-mode-single-doc.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 | $0.00072 | $0.01056 |
| Opus 5 | $0.00036 | $0.00528 |
| Sonnet 5 | $0.00014 | $0.00211 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
ba-mode-single-doc 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 4d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BA Mode A — ingest-from-single-doc
When to use
You are the BA and Shape Detection (Phase 1.0, in the BA agent router) selected Mode A: docs/SRS.md is one bulk document with User Story and FR content inline, and docs/user-stories/ + docs/frs/ are empty. Run this setup, then hand to the ingestion pipeline.
Phase 1.A — Mode ingest-from-single-doc setup
The incoming SRS is one bulk document with US and FR content inline (any source format — markdown, Word, plain text dropped into docs/SRS.md from an upstream paste). Your job is to restructure it into the kit's three-file shape before the common procedure runs.
A1. Identify inline US blocks. Walk SRS §3.2 looking for per-US sub-sections (#### [US-NNN] headers or equivalent). For each:
- Extract the US content (Description / Pre-conditions / Main Flow / Business Rules / Post-conditions).
- Write a new file at
docs/user-stories/US-NNN.mdperuser-story-template.md. - Replace the SRS §3.2 sub-section with an index-table row (ID / Title / one-line Description / Role / Priority / Linked FRs / Status).
A2. Identify inline FR blocks. Walk SRS §3.3 (or §3.4 if FRs were mixed into technical constraints in the upstream doc). For each FR with inline detail:
- Extract Description / Preconditions / Main Flow / Business Rules / schemas / Error Handling / sequence diagram.
- Write a new file at
docs/frs/FR-NNN.mdperfrs-template.md. - Replace the SRS §3.3 sub-section with an index-table row.
A3. Set Source: inline in the SRS header (this is the default for Mode A — the materialized files ARE the source of truth going forward; the upstream bulk doc is treated as input, not as an external system to sync against).
A4. Log the split in SRS §10 Changelog: <ISO-8601> | BA Mode A ingestion — split N inline User Stories into docs/user-stories/, M inline FRs into docs/frs/.
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.
- 4d ago First seen · 45 lines · 72 tokens per session scan A 15bcb3613d3b
ba-mode-single-doc is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,056 once invoked, about $0.0004 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.