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-init)<a href="https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/kb-init"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/kb-init/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-init"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/kb-init.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 | $0.00066 | $0.01845 |
| Opus 5 | $0.00033 | $0.00923 |
| Sonnet 5 | $0.00013 | $0.00369 |
| Haiku 4.5 | $0.00007 | $0.00185 |
Grade A, and why
kb-init 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 9d 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.
Initialise Knowledge Base
Set up a project to use the sdlc-knowledge-base plugin. This skill is idempotent — safe to run multiple times. It checks for existing setup before making changes.
Arguments
--with-starter-pack(default) — Seedlibrary/with three example library files synthesised from the Agentic SDLC research programme:agentic-sdlc-options.md,agent-suitability-rubric.md,specification-formality-and-agent-performance.md. New users get a queryable library on first install and can see the format end-to-end. The starter content is example only and meant to be replaced or extended.--empty— Create the library directory structure but skip the starter pack. Use when you want a completely empty library to populate from scratch.--library <path>— Initialise a library at this explicit path instead of./libraryand skip the CLAUDE.md append (the section assumes one library at the default path). Use for isolated testing or a secondary library. See #209.
Steps
1. Verify the plugin is installed
Check that the sdlc-knowledge-base plugin is available. If not, report:
sdlc-knowledge-base plugin is not installed. Run:
/plugin install sdlc-knowledge-base@ai-first-sdlc
Then re-run this skill.
2. Check for existing CLAUDE.md
The schema section gets appended to the project's CLAUDE.md. If CLAUDE.md does not exist, report:
CLAUDE.md not found in the project root. Create it first (even an empty file is fine), then re-run this skill.
3. Check for existing knowledge base section
Read CLAUDE.md and look for an existing ## Knowledge Base heading. If present, report:
[Knowledge Base] section already exists in CLAUDE.md. Skipping append.
If you want to reset the section, remove it manually and re-run this skill.
Then proceed to step 5 (directory creation) — it's still useful even if the section already exists.
4. Append the schema section template
Read the template from templates/claude-md-section.md (relative to this skill's directory; in plugin install this resolves to ${CLAUDE_PLUGIN_ROOT}/skills/kb-init/templates/claude-md-section.md).
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- templates/claude-md-section.md 9.4 KB
- templates/starter-pack/library/_shelf-index.md 4.7 KB
- templates/starter-pack/library/agent-suitability-rubric.md 6.1 KB
- templates/starter-pack/library/agentic-sdlc-options.md 6.4 KB
- templates/starter-pack/library/log.md 845 B
- templates/starter-pack/library/specification-formality-and-agent-performance.md 7.6 KB
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.
- 9d ago First seen · 185 lines · 66 tokens per session scan A 9d2cdc7e8033
kb-init is a skill published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,845 once invoked, about $0.0003 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 2026-08-30.
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…