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-layers)<a href="https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/kb-layers"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/kb-layers/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-layers"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/kb-layers.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 | $0.00047 | $0.00823 |
| Opus 5.5 | $0.00019 | $0.00329 |
| Sonnet 5.5 | $0.00009 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
kb-layers 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage KB Layer Vocabulary
Lightweight: This skill reads only index metadata and writes CLAUDE.md. Inline execution is acceptable — no agent dispatch needed.
Manage the project's allowed layer vocabulary for the layer: frontmatter field in library files.
Arguments
| Form | Description |
|---|---|
| (none) | List allowed layers with file counts from shelf-index |
--add <layer> |
Add a layer to the allowed set |
--remove <layer> |
Remove a layer (refused if any file uses it) |
--remove <layer> --force |
Remove a layer bypassing usage check |
Preflight
Read CLAUDE.md and locate the [Knowledge Base] section. Extract library_path (default library/) and shelf_index_path (default library/_shelf-index.md).
Steps
1. Resolve configuration
Read CLAUDE.md [Knowledge Base] section to resolve library_path and shelf_index_path.
2. Run kb_layers.py
python3 -c "
import sys, os, importlib.util
PLUGIN_ROOT = os.environ.get('CLAUDE_PLUGIN_ROOT', '')
SCRIPTS = os.path.join(PLUGIN_ROOT, 'scripts')
INIT = os.path.join(SCRIPTS, '__init__.py')
if os.path.isfile(INIT) and 'sdlc_knowledge_base_scripts' not in sys.modules:
spec = importlib.util.spec_from_file_location(
'sdlc_knowledge_base_scripts', INIT,
submodule_search_locations=[SCRIPTS])
if spec and spec.loader:
mod = importlib.util.module_from_spec(spec)
sys.modules['sdlc_knowledge_base_scripts'] = mod
spec.loader.exec_module(mod)
from sdlc_knowledge_base_scripts.kb_layers import main
args = ['--project-dir', '<project_dir>', '--shelf-index-path', '<shelf_index_path>']
# Append --add <layer>, --remove <layer>, or --force as appropriate
sys.exit(main(args))
"
Replace <project_dir> with the project root and <shelf_index_path> with the resolved path.
3. Report the result
Print the script output. For list mode:
# Project layer set
Mode: defaults
Allowed layers:
- methodology (15 files)
- evidence (22 files)
- domain ( 7 files)
- development ( 3 files)
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 · 93 lines · 47 tokens per session scan A 7e0f6749196e
kb-layers is a skill published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 15d ago), licensed MIT. It adds 47 tokens to every session and 823 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
notion
Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.
notion
Search, read, create, and update Notion pages via the Notion MCP.
recipe-create-doc-from-template
Copy a Google Docs template, fill in content, and share with collaborators.
bo-runbook
A reusable step-by-step operating manual for a repeated task or handoff. It covers prerequisites, normal steps, checks that show success, failure handling, and escalation when those details are provided.
reversa-sync
Convergência pós-coding do Reversa: destila a feature entregue num adendo em reversasdd/addenda/, mantendo a extração representativa entre re-extrações, sem tocar nos artefatos originais. Passo opcional do ciclo forward após /reversa-coding.
prismer-notion
Notion API + ntn CLI: pages, databases, markdown, Workers.