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.
npx agentmods add instructions/fy0/codekanban/agents-mdgit clone --depth 1 https://github.com/fy0/CodeKanbanWhat 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 | $0.00689 | $0.00689 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
CodeKanban 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
The entry point main.go wires CLI flags, service installation, and HTTP startup via server.go. HTTP handlers live in api/ with Huma schemas under api/h. Data access code resides in model/, where table/ hosts sample GORM models and sqlc_gen/ stores SQL schema plus codegen stubs. Shared helpers, configuration loaders, and logging adapters are kept in utils/ (see app_config.go for defaults). Static assets and generated docs land under static/ and docs/, both served via the embedded filesystem. Keep project-wide settings in config.yaml.
Build, Test, and Development Commands
go mod tidysyncs dependencies with the module definition.go run .starts the HTTP service; append-mto force migrations,-ior--uninstallfor Windows service management.go test ./...runs all package tests with race detection optional via-race.go generate -run "sqlc" ./model/sqlc_gen/...regenerates SQLC outputs before committing schema changes.go vet ./...catches common anti-patterns during review.
Coding Style & Naming Conventions
Target Go 1.24 and format every change with gofmt (or your editor's equivalent) before commit; gofmt's tab-based indentation is the single source of truth. Align imports with goimports to keep standard, third-party, and local packages grouped. Exported types and functions use PascalCase, private helpers use camelCase, and interface names should end in er when they describe behavior. Match file names to the package or domain (config_service.go, user_handler.go) to ease discovery. Keep log messages structured, using zap fields instead of printf-style strings.
Testing Guidelines
Place _test.go files next to the code under test and mirror package names to avoid import cycles. Prefer table-driven tests for handlers and utilities; use github.com/DATA-DOG/go-sqlmock when exercising database logic. Validate HTTP routes with Fiber's test utilities, asserting both status codes and response envelopes defined in api/h/response.go. Before opening a PR, run go test ./... (add -race and -count=1 for flake-sensitive code) and ensure migrations leave databases clean.
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.
- 2d ago First seen · 24 lines · 689 tokens per session scan A bb9c87ca5559
CodeKanban AGENTS.md is an instructions file published in the GitHub repository fy0/CodeKanban (225 stars, last pushed 3d ago), licensed Apache-2.0. It adds 689 tokens to every session, about $0.0034 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.
Other instructions, from other repositories
forge AGENTS.md
Instructions for automagik-dev/forge, covering genie agent framework, core identity, core purpose, task context (auto-loaded) and product documentation.
forge CLAUDE.md
Instructions for automagik-dev/forge, a project described as: The Vibe Coding++™ platform - orchestrate multiple AI agents, experiment with isolated attempts, ship code you understand. Multi-agent kanban with MCP integration.
coding-agents AGENTS.md
AGENTS.md instructions for panquequelol/coding-agents, covering asd-ste100, code and agents.
FastVibe CLAUDE.md
Instructions for zzdhybthu/FastVibe, a project described as: A lightweight Code Agent orchestration hub with multi-repo management, task queuing, Git worktree automation, and real-time Web UI interaction.
helmor AGENTS.md
Instructions for dohooo/helmor, covering agents.md, what is helmor, commands, architecture and three-process model.
veritas-kanban AGENTS.md
Instructions for BradGroux/veritas-kanban, covering agents.md — canonical agent instructions for veritas kanban, runtime requirements, repository layout, essential commands and install.