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-external-sourcenpx skills add evolplus/talos --skill ba-mode-external-sourcegit clone --depth 1 https://github.com/evolplus/talosWhat 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 | $0.00076 | $0.01146 |
| Opus 5 | $0.00038 | $0.00573 |
| Sonnet 5 | $0.00015 | $0.00229 |
| Haiku 4.5 | $0.00008 | $0.00115 |
Grade A, and why
ba-mode-external-source 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BA Mode C — ingest-from-external-source
When to use
You are the BA and Shape Detection selected Mode C: the SRS content lives in an external system reached via an MCP connector. Materialize it into the kit's three-file shape, record provenance in the SRS header, then hand to the pipeline. Includes the re-ingestion path for subsequent runs.
Phase 1.C — Mode ingest-from-external-source setup
The SRS content lives in an external system (Confluence, Notion, Jira, SharePoint, …) and is reached via an MCP connector. Your job is to materialize the external content into the kit's three-file shape, record provenance in the SRS header, and then proceed.
C1. Identify the Source URL. The dispatch input names the source (e.g., confluence://wiki.example.com/spaces/PROD/pages/12345). If absent, return NEEDS_CONTEXT to the Orchestrator requesting the URL.
C2. Fetch via MCP. Use the appropriate MCP tool (Confluence / Notion / Jira / SharePoint connectors are documented in .claude/mcp-readers/ if present; if no reader is documented for the source type, file an open-issue requesting reader documentation, then return NEEDS_CONTEXT). Capture the full content + a content hash (e.g., SHA-256 of the rendered text).
C3. Materialize into kit format. Depending on the upstream shape: if the external content is one bulk page → drop it into docs/SRS.md and run Mode A steps (A1–A4) on the materialized content. If the external space has a page tree (one SRS-overview page + child pages per US / per FR) → write to docs/SRS.md + docs/user-stories/*.md + docs/frs/*.md directly, then continue.
C4. Record provenance in the SRS header:
Source: <url>— the external URL pulled from.Source-Last-Pulled: <ISO-8601>— when this materialization happened.Source-Hash: <hash>— content hash captured in C2.
C5. Log the ingest in SRS §10 Changelog: <ISO-8601> | BA Mode C ingestion from <url>; Source-Hash: <hash>.
C6. Gap detection (no invention). After materialization, walk the resulting SRS against the kit's required-section list. External sources are often skeletons (a Confluence page with ## Security heading and no body content under it). Missing required field → TODO: <field expected> marker + paired OQ in SRS §8. Never fill from "common sense" or default assumptions about what the external source "would have said." The external source is the only authority; if it didn't say something, neither does the synthesized SRS.
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.
- 2d ago First seen · 50 lines · 76 tokens per session scan A 35f33cc95bf2
ba-mode-external-source is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 28d ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,146 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
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.