kanban-md: Instructions file for Codex

AGENTS.md

kanban-md AGENTS.md is an instructions file for Codex, OpenCode from antopolskiy/kanban-md. It costs 3,421 tokens per session, scanned A, original, MIT.

Contributor instructions for a Markdown kanban project, where tasks are managed as cards or columns in Markdown files. They cover code changes, research records, releases, and synchronized instruction files.

In plain words
What is it for?
Updating README files, recording research reports, writing semantic commits, running the required checks, and releasing through the automated tag workflow.
Why use it?
They reduce mistakes in documentation, testing, research tracking, and release publishing.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

This is antopolskiy/kanban-md's own configuration. It tells Codex and OpenCode how to work on kanban-md 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-md configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is git worktree add ../kanban-md-task-<ID> -b task/<ID>-<kebab-description>.

Reuse

Borrowing it

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

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-md AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/antopolskiy/kanban-md/agents-md"><img src="https://agentmods.dev/badge/instructions/antopolskiy/kanban-md/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,421 This file is loaded in full into every session.
When invoked 3,421 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 $0.03421 $0.03421
Opus 5 $0.01710 $0.01710
Sonnet 5 $0.00684 $0.00684
Haiku 4.5 $0.00342 $0.00342

Measured 10d ago against content hash 9a6ad1c45436, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

kanban-md 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 10d 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.

AGENTS.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guidelines

Note: CODEX.md and CLAUDE.md are symlinks to AGENTS.md. Only edit AGENTS.md — both files are always in sync.

  • Use semantic commit format, e.g.
feat: <short description>

Detailed description of the changes, that can be multiline, but do not artificially create line breaks, as commit messages are automatically wrapped.
- Use bullet points
- When needed
  • When making changes that affect user-facing behavior (new commands, new flags, changed defaults, new installation methods, etc.), update README.md to reflect those changes.

  • Whenever any research is done (including by the subagents), it should be documented as a report in docs/research/YYYY-MM-DD-.md. In case of subagents, the need to be instructed to create the report file and on completion return only the path to the report, so that the main agent can read and analyze it.

Releasing

To release a new version, tag and push. The release workflow triggers automatically on tag push — do NOT also run gh workflow run release, as that causes a duplicate build.

IMPORTANT: Never create releases locally with gh release create. Always let goreleaser handle release creation through the CI pipeline. After tagging and pushing, wait for the workflow to complete, then use gh release edit to update the release notes.

Version numbering: Decide the version number autonomously based on semver (patch for fixes, minor for features, major for breaking changes). Do not ask the user to confirm the version.

git tag vX.Y.Z
git push origin main --tags

CI verification (required)

After pushing the tag, watch the GitHub Actions release workflow:

gh run list --workflow release --limit 10
gh run watch <RUN_ID>

If the workflow fails:

  1. Inspect logs:
    gh run view <RUN_ID> --log-failed
    
  2. Fix the underlying issue in main (code/tests/lint/goreleaser config, etc.).
  3. Re-run the release by tagging a new version and pushing tags (preferred), or rerun the failed run only if it was clearly transient:
    • Preferred:
      git tag vX.Y.Z+1
      git push origin main --tags
      
    • Transient-only rerun:
      gh run rerun <RUN_ID> --failed
      

Read the full file on GitHub · 279 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. 10d ago First seen · 279 lines · 3,421 tokens per session scan A 9a6ad1c45436

Subscribe to this mod's changes

kanban-md AGENTS.md is an instructions file published in the GitHub repository antopolskiy/kanban-md (214 stars, last pushed 16d ago), licensed MIT. It adds 3,421 tokens to every session, about $0.0171 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.