A workflow for updating a project's knowledge base after code changes. A knowledge base is a set of project documents covering requirements, design, terms, and behavior.

It helps inspect recent commits, review diffs, identify affected concepts, and update the relevant knowledge-base files or report conflicts with the specification.

It compares recent code changes with the documented specifications so new or changed behavior is recorded without silently weakening existing requirements.

kb-update — Skill for Claude Code by mathiasbourgoin

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.

Any agent

npx skills add mathiasbourgoin/roster --skill kb-update

Clone the repo

git clone --depth 1 https://github.com/mathiasbourgoin/roster

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mathiasbourgoin/roster/kb-update.svg)](https://agentmods.dev/skills/mathiasbourgoin/roster/kb-update)

Your own site

<a href="https://agentmods.dev/skills/mathiasbourgoin/roster/kb-update"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/kb-update.svg" alt="Measured on agentmods" height="20"></a>

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 949 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.00949
Opus 5	$0.00010	$0.00475
Sonnet 5	$0.00004	$0.00190
Haiku 4.5	$0.00002	$0.00095

Measured yesterday against content hash d6bbae5a4bc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

kb-update 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 yesterday.

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.

.agents/skills/kb-update/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KB Update

Synchronize the project knowledge base with recent changes. This is the standalone invocable version of the KB agent's update mode.

Steps

1. Read KB Structure

Run the claims reconciler's audit --root . subcommand when either scripts/claims-reconcile.js or .harness/bin/claims-reconcile.js is available. Treat specs/*.md, specs/claims-authority.json, and specs/claims.lock as authoritative inputs; generated KB files are views, never evidence for their own source claims.
Read kb/index.md to understand the KB layout and file purposes.
Identify all KB files: spec.md, properties.md, glossary.md, architecture.md, and any domain-specific files listed in the index.

2. Identify Recent Changes

Run git diff HEAD~5..HEAD --name-only to find recently changed source files (adjust range if user specifies).
Run git diff HEAD~5..HEAD for the actual diffs.
Identify which KB-relevant concepts were touched (new types, changed APIs, modified invariants, renamed terms).

3. Compare Code Against KB

For each changed concept, classify the delta:

Delta Type	Action
Code contradicts KB spec	FLAG AS ERROR. Do NOT update KB. Report: "Code at `<file>:<line>` violates spec: `<quote>`. Fix the code or open a spec amendment discussion."
Code extends KB (new feature, new term)	Add entries to relevant KB files. Update `kb/index.md` if new files created.
Code refines existing concept	Update the KB entry with more precise language. Preserve or strengthen existing properties.
KB entry has no corresponding code	Flag as potentially stale. Do not remove — ask the user.

4. Apply Updates

When the claims reconciler is installed, do not hand-edit generated normative sections in kb/spec.md, kb/properties.md, or kb/index.md. Amend the authoritative spec or metadata, validate it, then run the reconciler's project --root . subcommand.
Preserve the optional code-intel block in kb/properties.md; the projector owns the rest of that generated file.
For each KB file modified, update the frontmatter last-updated field to today's date.
Add cross-references between related entries.
Ensure new terms are added to kb/glossary.md with definitions.

Read the full file on GitHub · 82 lines

Files

What ships with it

1 file 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.

.roster-managed 0 B

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.

yesterday Changed · +11 lines · +3 tokens per session d6bbae5a4bc5
7d ago First seen · 71 lines · 18 tokens per session scan A 7176f03b0d4c

Subscribe to this mod's changes

kb-update is a skill published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 949 once invoked, about $0.0001 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.

Writing and docs

systematic-debugging

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

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 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

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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