kanban-agent: Instructions file for Codex

AGENTS.md

kanban-agent AGENTS.md is an instructions file for Codex, OpenCode from gak4u/kanban-agent. It costs 764 tokens per session, scanned A, original, MIT.

Repository instructions for a kanban and worker-tracking project. They explain where documentation belongs, how to keep it current, and how to record durable project knowledge.

In plain words
What is it for?
They help maintain project overviews, architecture notes, decision logs, wiki pages, and shared glossary or memory records.
Why use it?
They give coding agents consistent rules for updating project documentation instead of leaving the repository's status and decisions out of date.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions AGENTS.md.

This is gak4u/kanban-agent's own configuration. It tells Codex and OpenCode how to work on kanban-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kanban-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gak4u/kanban-agent. 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/gak4u/kanban-agent/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/gak4u/kanban-agent

Made for: Codex, OpenCode.

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.

agentmods badge for kanban-agent AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gak4u/kanban-agent/agents-md/github.svg)](https://agentmods.dev/instructions/gak4u/kanban-agent/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/gak4u/kanban-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/gak4u/kanban-agent/agents-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.

agentmods 80×15 button for kanban-agent AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gak4u/kanban-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/gak4u/kanban-agent/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 764 This file is loaded in full into every session.
When invoked 764 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00764 $0.00764
Opus 5.5 $0.00306 $0.00306
Sonnet 5.5 $0.00153 $0.00153
Haiku 4.5 $0.00076 $0.00076

Measured today against content hash 6bfef763fade, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kanban-agent 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 today.

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 · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - worker-tracker

Working guide for any agent (or person) in this repo. Read this first.

Project: worker-tracker · Org: jQode · Repo: [email protected]:gak4u/kanban-agent · Scaffolded 2026-11-16 kanban-agent: MCP kanban/worker tracking server

Documentation lives in this repo

docs/ is the source of truth. Keep it current as the code changes.

  • docs/README.md - the living overview. What this is, how to run it, current state. Update it whenever that changes.
  • docs/architecture.md - how it is built: components, data flow, the decisions that shaped it.
  • docs/decisions.md - a dated log. Append new decisions with a date; do not rewrite old ones.
  • docs/wiki/ - topic pages for cross-cutting notes and gotchas. One topic per file, kebab-case. Link pages with [[page-name]].

Rule: when you change something the docs record (a feature ships or is withdrawn, config or a rail changes, a known issue is fixed or found), edit the matching section and its "Last updated" date before you finish. Do not keep a parallel Notion wiki for this project - Notion indexes, the repo holds the truth.

Wider context: the global glossary

Every durable operator memory across all machines is indexed in Notion as Knowledge Base -> Memory Index:

https://app.notion.com/p/41a4549d8bef8163bf07f26771aa6c54

Use it when you need context beyond this repo - how another project, org or host works, a shared convention, a gotcha already learned elsewhere. Filter by Org (jQode / Tesseract / IXG / SKWAD / Personal) or Area, read the rows; each row carries its Repo, Project folder and Source path.

Pull only what you need - do not drag unrelated context in.

Local fallbacks when Notion is not reachable (e.g. inside a sandboxed engine):

  • the per-project memory store ~/.claude/projects/<dir>/memory/*.md (each file is one fact, frontmatter: name, description, type)
  • the Hermes wiki ~/HermesDrive/wiki

Feeding the glossary back

When you learn a durable, non-obvious fact about this project that a future session would want (a constraint, a gotcha, where something lives), write it as a memory file under this machine's ~/.claude/projects/<dir>/memory/ with name / description / type frontmatter. It flows into the Notion index on the next machine sync. Keep it one fact per file; link related facts with [[name]].

Read the full file on GitHub · 44 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. today First seen · 44 lines · 764 tokens per session scan A 6bfef763fade

Subscribe to this mod's changes

kanban-agent AGENTS.md is an instructions file published in the GitHub repository gak4u/kanban-agent (0 stars, last pushed 2d ago), licensed MIT. It adds 764 tokens to every session, about $0.0031 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 2026-11-17.

Related

kanban-agent AGENTS.md compared with instructions from other repositories

kanban-agent AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kanban-agent AGENTS.mdgak4u/kanban-agentInstructions file02d agoMITA764Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot