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/usekaneo/kaneo/agents-mdgit clone --depth 1 https://github.com/usekaneo/kaneoWrote 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.
[](https://agentmods.dev/instructions/usekaneo/kaneo/agents-md)<a href="https://agentmods.dev/instructions/usekaneo/kaneo/agents-md"><img src="https://agentmods.dev/badge/instructions/usekaneo/kaneo/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02008 | $0.02008 |
| Opus 5 | $0.01004 | $0.01004 |
| Sonnet 5 | $0.00402 | $0.00402 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade A, and why
kaneo 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 4d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kaneo agent guide
Kaneo is a fast, deliberately simple, self-hosted project-management platform. The Hono API owns domain behavior and authorization, the React app consumes its typed client, PostgreSQL stores durable state, and events plus WebSockets keep clients current. Redis is optional and coordinates realtime delivery across multiple API instances.
This is an operating guide, not a README. These rules are good defaults; explicit developer and user instructions take precedence.
Principles
- Simplicity is a product requirement. Build the smallest model that makes correct behavior obvious.
- Features should solve a real problem without making routine work heavier.
- Protect performance, especially on task-heavy boards and realtime views.
- Keep self-hosting straightforward and single-instance deployments first-class. Do not make Redis or another managed service mandatory without an explicit product decision.
- Support both bundled same-origin deployments and separately hosted API and web deployments.
- Protect user data, workspace boundaries, and authorization checks.
- Read the relevant implementation before changing it. Follow an established local pattern when it fits, but do not preserve accidental complexity merely because it exists.
- Stay focused. Do not mix requested work with speculative features, broad refactors, or unrelated cleanup.
Architecture
apps/api— Hono API, Better Auth, controllers, database access, events, integrations, MCP HTTP routes, and WebSockets.apps/web— React/Vite UI, TanStack Router and Query, fetchers, hooks, and realtime cache updates.apps/docs— product and API documentation content;apps/site— public Next.js site and documentation host.packages/libs— shared typed Hono client and URL helpers.packages/permissions— canonical permission vocabulary and built-in roles.packages/mcp— published stdio MCP package.charts/kaneo— Helm deployment surface.tests/apicontains API unit tests;tests/api-integrationcontains PostgreSQL-backed integration tests.
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.
- 4d ago First seen · 126 lines · 2,008 tokens per session scan A c6907ce385ad
kaneo AGENTS.md is an instructions file published in the GitHub repository usekaneo/kaneo (8,940 stars, last pushed yesterday), licensed MIT. It adds 2,008 tokens to every session, about $0.0100 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
core CLAUDE.md
Claude Code instructions for module-federation/core, covering claude task parallelization & development guidelines, core principles, maximum parallelization strategy, universal parallel task patterns and for any codebase task.
orval AGENTS.md
AGENTS.md instructions for orval-labs/orval, covering using vite+, the unified toolchain for the web, built-in commands vs scripts, tool versions and review checklist.
ui-components AGENTS.md
AGENTS.md instructions for starc007/ui-components, covering beui v2 — agent guide, commands, layout, component catalog and components (motion category — primitives).
n8n CLAUDE.md
Claude Code instructions for n8n-io/n8n, a project described as: Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
ProductFlow AGENTS.md
AGENTS.md instructions for yuqie6/ProductFlow, covering trellis instructions, repository guidelines, project structure & module organization, build, test, and development commands and coding style & naming conventions.
walkerOS CLAUDE.md
Claude Code instructions for elbwalker/walkerOS, covering claude.md and important: use agent.md.