kb-discover

A tool that reads source code to uncover project knowledge that was never written down, such as architecture, naming rules, API agreements, configuration formats, and testing practices. It records these findings as knowledge-base articles.

In plain words
What is it for?
Use it to document how the code works, preserve project conventions, and explain interfaces and configuration by examining the implementation.
Why use it?
It gives future developers useful guidance when the codebase lacks complete or reliable documentation.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/charlesjones-dev/claude-code-plugins-dev/kb-discover
Any agent
npx skills add charlesjones-dev/claude-code-plugins-dev --skill kb-discover
Clone the repo
git clone --depth 1 https://github.com/charlesjones-dev/claude-code-plugins-dev

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,458 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.04458
Opus 5 $0.00017 $0.02229
Sonnet 5 $0.00007 $0.00892
Haiku 4.5 $0.00003 $0.00446

Measured 2d ago against content hash 1fc6cf73e6ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kb-discover 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.

plugins/ai-knowledge/skills/kb-discover/SKILL.md · 370 lines

How it starts

The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Base Discover

You are a codebase knowledge archaeologist. Your job is to analyze source code — not documentation — and extract the implicit knowledge embedded in it: architecture patterns, naming conventions, error handling strategies, API contracts, configuration structures, data models, testing patterns, and unwritten rules. This knowledge is then distilled into KB articles so future Claude Code sessions understand how the codebase actually works, even when no documentation exists.

This fills a gap the other KB skills don't cover:

  • /kb-absorb and /kb-ingest work with existing markdown documentation
  • /kb-harvest pulls from external docs and URLs
  • /kb-discover mines the source code itself for knowledge that was never written down

Frontmatter Schema

Every KB file MUST have valid YAML frontmatter:

---
tags: [architecture, api, conventions]     # Required: lowercase tags for discovery
related: [[other-kb-file]]                 # Optional: cross-references to related KB files
created: YYYY-MM-DD                        # Required: date created
last-updated: YYYY-MM-DD                   # Required: date last modified
pinned: false                              # Optional: true = always loaded. Default false
scope:                                     # Optional: glob pattern(s) for auto-matching. String or array.
  - "src/api/**"
  - "src/middleware/**"
discovered-from: "src/api/, src/models/"   # Required for discovered content: directories/files analyzed
---

The discovered-from field tracks which parts of the codebase were analyzed to produce the KB entry. This enables re-discovery if the codebase evolves significantly.

Resolving today's date (cross-platform, CRITICAL): Never guess, infer, or increment prior dates. When this skill writes created / last-updated, resolve today's date once at the start of the write phase, then reuse that single value for every write. Try these commands in order and use the first that returns a YYYY-MM-DD string:

Read the full file on GitHub · 370 lines

Changes

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.

  1. 2d ago First seen · 370 lines · 34 tokens per session scan A 1fc6cf73e6ab

Subscribe to this mod's changes

kb-discover is a skill published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (34 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 4,458 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

gwm

Manage git worktrees across any repository with the gwm Rust binary (CLI + ratatui TUI). Use when the user asks to create / list / remove / bootstrap / switch / link worktrees, run a command across worktrees (gwm exec) or reclaim build artifacts (gwm clean), materialise a PR into a worktree (gwm review), drive a…

kbrdn1/gwm-cli · 379 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens