What is veritas-kanban CLAUDE.md?

Repository instructions for Claude Code, an AI coding assistant, in the Veritas Kanban project. They add Claude-specific lessons to the main AGENTS.md guide, including security and architecture notes.

Use them when Claude Code works on Veritas Kanban, especially when changing authentication, handling file paths, or checking project setup.

They prevent Claude from repeating known mistakes or conflicting with the project's main rules. They also point it to the current tool versions and security checks.

How BradGroux/veritas-kanban configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to BradGroux/veritas-kanban. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/BradGroux/veritas-kanban/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/BradGroux/veritas-kanban

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/instructions/bradgroux/veritas-kanban/claude-md/github.svg)](https://agentmods.dev/instructions/bradgroux/veritas-kanban/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/bradgroux/veritas-kanban/claude-md"><img src="https://agentmods.dev/badge/instructions/bradgroux/veritas-kanban/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bradgroux/veritas-kanban/claude-md"><img src="https://agentmods.dev/badge/instructions/bradgroux/veritas-kanban/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 590 This file is loaded in full into every session.

When invoked 590 The same file — it is already loaded in full.

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	$0.00590	$0.00590
Opus 5.5	$0.00236	$0.00236
Sonnet 5.5	$0.00118	$0.00118
Haiku 4.5	$0.00059	$0.00059

Measured 2mo ago against content hash 15d16ffd915b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

veritas-kanban CLAUDE.md 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 2mo 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.

CLAUDE.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Claude-Specific Supplement for Veritas Kanban

Canonical instructions are in AGENTS.md. Read that file first. This supplement contains Claude-specific lessons and common mistakes caught by previous Claude runs. Do not duplicate AGENTS.md content here.

Last updated: 2026-08-30 (v6.1.3 release freshness) Freshness check: Update after mistakes; review monthly.

What changed in v2.1

AGENTS.md is now the canonical project instruction file. It supersedes the duplicate context that was previously embedded here. The fields updated from their stale v2.0 values:

pnpm: was 9+ → now ≥ 11.0.0 (pinned [email protected])
Node: was 22+ → now ≥ 22.22.1
Providers: managed Buzz, Grok Build, Codex, Claude Code, Copilot CLI, Hermes, and OpenClaw contracts are documented in AGENTS.md

Lessons learned (Claude-specific)

Security

❌ Forgot global middleware — flagged missing per-route auth that was already in app.use(). Global middleware is in server/src/middleware/; check there before adding per-route auth.
❌ Used path.join() without validation — allows ../ traversal. Always follow with validatePathSegment() + ensureWithinBase().

Architecture

❌ Imported fs directly in service files — breaks storage abstraction.
❌ Added polling when WebSocket hook existed — use useRealtimeAgentStatus.
❌ Frontend interface didn't match server response (totalAgents vs total). Server response is the source of truth; interfaces must match exactly.
❌ Agent provider guessing — always verify flag names and interfaces against versioned docs before implementing a new provider adapter.

Testing

❌ Used wrong schema field in test fixtures (status: "success" vs success: true). Copy fixture shapes from live runtime output or type definitions, not from memory.
✅ pnpm-lock.yaml is generated by pnpm; never reformat or hand-edit it.

Multi-agent runtime

Heartbeat timeout: 5 min. Stale-check interval: 1 min.
Activity source of truth: status-history files, not activity.json.
Dashboard optimistic updates: use onMutate, not refetch-after-mutate.

Read the full file on GitHub · 65 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.

2mo ago First seen · 65 lines · 590 tokens per session scan A 15d16ffd915b

Subscribe to this mod's changes

veritas-kanban CLAUDE.md is an instructions file published in the GitHub repository BradGroux/veritas-kanban (851 stars, last pushed 4d ago), licensed MIT. It adds 590 tokens to every session, about $0.0024 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 2026-08-30.

Project Management ai-agents developer-tools kanban local-first pino

veritas-kanban CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
veritas-kanban CLAUDE.mdBradGroux/veritas-kanban	Instructions file	851	4d ago	MIT	A	590	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

veritas-kanban: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md — Claude-Specific Supplement for Veritas Kanban

What changed in v2.1

Lessons learned (Claude-specific)

Security

Architecture

Testing

Multi-agent runtime

What this file has done since we first saw it

veritas-kanban CLAUDE.md compared with instructions from other repositories