kanban-lite AGENTS.md

Repository-wide development instructions for kanban-lite, a tool that manages kanban boards stored in Markdown files or SQLite. They cover shared behavior across its API, command-line tool, and MCP server.

In plain words
What is it for?
Use them when modifying kanban-lite code, especially shared SDK behavior, plugins, provider features, React or TypeScript files, and user-facing documentation.
Why use it?
They keep changes consistent across interfaces and set rules for file size, module structure, documentation, and verification.

Instructions file for CodexOpenCode

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 instructions/borgius/kanban-lite/agents-md
Clone the repo
git clone --depth 1 https://github.com/borgius/kanban-lite

Made for: Codex, OpenCode.

Per session 431 This file is loaded in full into every session.
When invoked 431 The same file — it is already loaded in full.
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 $0.00431 $0.00431
Opus 5 $0.00216 $0.00216
Sonnet 5 $0.00086 $0.00086
Haiku 4.5 $0.00043 $0.00043

Measured yesterday against content hash 2f5d6449f0f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kanban-lite AGENTS.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 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.md · 26 lines

What it actually says

Kanban Markdown - Development Guide

A VSCode extension + standalone server + CLI + MCP server for managing kanban boards stored as markdown files (default) or SQLite.

Repo-wide defaults

  • The SDK is the source of truth for shared business logic. Keep API, CLI, and MCP behavior in feature parity when a capability changes.
  • Keep index.ts files as barrel-only entrypoints: do not add implementation logic, conditionals, helpers, or side effects there; move real behavior into named modules and only re-export from index.ts.
  • Make surgical edits only: avoid unrelated refactors, large rewrites, or new dependencies unless the task clearly needs them.
  • No source file may exceed 600 lines (excluding generated files, test fixtures, and *.d.ts declarations). Split oversized modules before adding more logic.
  • For user-facing changes, update README.md and CHANGELOG.md, and regenerate generated docs from source comments or route metadata instead of editing generated docs directly.
  • Use the scoped instructions in .github/instructions/ and repo skills for React/TSX work, kanban core surface changes, capability/provider invariants, plugin option schemas, and reliability-sensitive flows.

Post-change verification (mandatory)

After every code change, before marking a task complete:

  1. TypeScript — run pnpm exec tsc --noEmit (or the package-scoped equivalent) and fix all errors and warnings introduced by the change.
  2. Build — confirm the project builds successfully (nr build or pnpm build); do not proceed if the build fails.
  3. Unit tests — run nr test and fix any failing tests introduced by the change.
  4. E2E tests — run nr e2e and fix any failing tests introduced by the change.

A task is not complete until all four checks pass with no new failures. Do not hand back to the user with red tests or build errors.

Goal: complete the tasks with the smallest possible code changes and minimal token usage.

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. yesterday First seen · 26 lines · 431 tokens per session scan A 2f5d6449f0f4

Subscribe to this mod's changes

kanban-lite AGENTS.md is an instructions file published in the GitHub repository borgius/kanban-lite (7 stars, last pushed 3mo ago), licensed MIT. It adds 431 tokens to every session, about $0.0022 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.