Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add SteveGJones/ai-first-sdlc-practices/plugin install sdlc-knowledge-baseWrote 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/stevegjones/ai-first-sdlc-practices/kb-promote-answer-to-library)<a href="https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/kb-promote-answer-to-library"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/kb-promote-answer-to-library/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/stevegjones/ai-first-sdlc-practices/kb-promote-answer-to-library"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/kb-promote-answer-to-library.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 | $0.00058 | $0.03237 |
| Opus 5.5 | $0.00023 | $0.01295 |
| Sonnet 5.5 | $0.00012 | $0.00647 |
| Haiku 4.5 | $0.00006 | $0.00324 |
Grade A, and why
kb-promote-answer-to-library 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 1mo 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 — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promote Answer to Library
When the librarian answers a query well — a comparison, an analysis, a connection between findings the library hadn't explicitly captured — that answer is itself valuable. It shouldn't disappear into chat history. This skill files the answer back into the library as a new page so explorations compound just like ingested sources do.
This is Karpathy's "good answers can be filed back into the wiki as new pages" insight from the LLM Wiki gist.
Arguments
- Query result (required) — the text of the answer to file. Can be:
- A file path containing the answer
- The answer text passed inline
- The output of a recent
kb-queryinvocation (when called withkb-query --promote-to-library, this is automatic)
--title <title>(optional) — explicit title for the new library file. If omitted, derive from the query that produced the answer (extract from the answer's heading or first paragraph).--path <library-file-path>(optional) — explicit destination path. If omitted, derive from the title using kebab-case conversion (e.g.,library/cycle-time-and-pi-planning.md).--target <handle>(optional) — the registered library handle to promote into. When omitted, promotes to the local library (default behaviour, backwards compatible). When set to a registered external library handle:- The handle must resolve in
~/.sdlc/global-libraries.json - The library must be filesystem type (remote-agent rejected)
- The library's directory must be writeable
- The promotion writes a new file there + updates that library's shelf-index
- The handle must resolve in
Preflight
- Verify the knowledge base is configured.
- Verify the destination path doesn't already exist (no overwriting; if the user wants to update an existing file, they edit it directly and run
kb-rebuild-indexes).
Steps
1. Parse the answer
Extract from the answer text:
- The claim or topic (becomes the file's
## Key Questionanswer) - The supporting findings with their citations (becomes
## Core Findings) - Any caveats or contradictions noted (becomes part of
## Design Principlesor a dedicated## Caveatssubsection) - The library files the librarian referenced (becomes the
derived_fromfrontmatter andcross_references)
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.
- 1mo ago First seen · 333 lines · 58 tokens per session scan A 5420df9bca50
kb-promote-answer-to-library is a skill published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 15d ago), licensed MIT. It adds 58 tokens to every session and 3,237 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
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…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when built-in search is thin. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.