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 evolplus/talos --skill ba-ingestion-pipelinegit 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-ingestion-pipeline)<a href="https://agentmods.dev/skills/evolplus/talos/ba-ingestion-pipeline"><img src="https://agentmods.dev/badge/skills/evolplus/talos/ba-ingestion-pipeline/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/evolplus/talos/ba-ingestion-pipeline"><img src="https://agentmods.dev/badge/skills/evolplus/talos/ba-ingestion-pipeline.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 | $0.00103 | $0.14475 |
| Opus 5 | $0.00051 | $0.07237 |
| Sonnet 5 | $0.00021 | $0.02895 |
| Haiku 4.5 | $0.00010 | $0.01448 |
Grade A, and why
ba-ingestion-pipeline 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 10d 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 — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BA Ingestion Pipeline — Phase 1.X common + Phase 1.Z delta + Phase 2 sign-off
When to use
You are the BA and you have finished a mode-specific setup skill (Mode A/B/C/D/E/F). Run the common procedure that applies to every ingestion dispatch: Phase 1.X (structural + pairing + self-containment + external-integration + Design-Flow/Guideline + Frontend-Framework + Backend-Track/Framework), Phase 1.Z (delta detection / iteration trigger), and Phase 2 (sign-off gate). If Phase 1.Z produces a diff, the iteration is planned via the ba-iteration-planning skill on a later dispatch.
Phase 1.X — Common Procedure (all modes)
-
Structural conformance check. Compare the incoming SRS against
.claude/agents/_templates/_artifacts/srs-template.mdas the structural baseline. Verify the following top-level sections exist (even if empty placeholders):- Header block: H1 title, Version, Domain, Author, Status, Last-Updated, Signed-off-by, Designated Design Approver, Design-Flow, Design-Guideline, Frontend-Framework, Backend-Track, Backend-Framework, Designated Dependency Approver
- § 1 Executive Summary
- § 2 Business Requirements Document (BRD)
- § 3 Functional Requirements (with §3.1 Domain Specification, §3.2 User Stories, §3.3 FRS, §3.4 Technical Constraints & Interface)
- § 4 Non-Functional Requirements (with §4.1 Security & Compliance when triggered)
- § 5 User Roles & Permissions
- § 6 User Activity Logging & Tracking Specification
- § 7 Definition of Done (DoD)
- § 8 Open Questions & Clarifications
- § 9 Resolved Questions
- § 10 Changelog
For UI-bearing SRSs, also verify §3.4.1 Design References, §3.4.2 UI Introspection Profile, and §3.4.3 Acceptance of Non-Introspectable Surfaces (the last only when §3.4.2 contains Partial or None rows).
For SRSs with any API surface (HTTP REST / gRPC / GraphQL / async messaging), also verify §3.4.4 API Contract Format. Required when at least one FR exposes an endpoint or message contract. If §3.4.4 is missing AND the SRS has any FR with Input Schema / Output Schema / Error Handling implying an external interface, raise an OQ in §8 with category
api-contract-format-undeclared: "Project has APIs (FRs: ) but §3.4.4 API Contract Format is not declared. Default would beopenapi-3.1for REST endpoints; explicit declaration required per CLAUDE.md §10. Suggested resolution: (a) declare openapi-3.1 if REST; (b) declare proto3 / graphql-sdl for gRPC / GraphQL; (c) ADR-justified markdown for legacy / prototype scope only.
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.
- 10d ago First seen · 534 lines · 103 tokens per session scan A e02de86ed47f
ba-ingestion-pipeline is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 103 tokens to every session and 14,475 once invoked, about $0.0005 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…