Borrowing it
Nothing to install: this file belongs to abuiles/agents-kanban. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/abuiles/agents-kanban/main/AGENTS.mdgit clone --depth 1 https://github.com/abuiles/agents-kanbanWrote 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/abuiles/agents-kanban/agents-md)<a href="https://agentmods.dev/instructions/abuiles/agents-kanban/agents-md"><img src="https://agentmods.dev/badge/instructions/abuiles/agents-kanban/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.
<a href="https://agentmods.dev/instructions/abuiles/agents-kanban/agents-md"><img src="https://agentmods.dev/badge/instructions/abuiles/agents-kanban/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00427 | $0.00427 |
| Opus 5.5 | $0.00171 | $0.00171 |
| Sonnet 5.5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
agents-kanban 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 2mo 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.
What it actually says
AGENTS.md
Scope
This repo runs on Cloudflare Workers.
Do not rely on memory for Cloudflare APIs, limits, bindings, or product behavior. Check current docs first.
Cloudflare docs
Use the official docs for any Workers-related work:
https://developers.cloudflare.com/workers/https://docs.mcp.cloudflare.com/mcp
For limits and quotas, use the product-specific platform/limits page.
Examples:
https://developers.cloudflare.com/workers/platform/limits/https://developers.cloudflare.com/d1/platform/limits/
Products covered by this rule
Always refresh docs before changing code that touches:
- Workers
- Durable Objects
- KV
- R2
- D1
- Queues
- Vectorize
- Workers AI
- Agents SDK
- AI Gateway
Commands
Common commands in this repo:
yarn testyarn typechecknpx wrangler devnpx wrangler deploynpx wrangler types
If bindings change in wrangler.jsonc, run:
npx wrangler types
Validation before commit or push
Before committing or pushing code changes:
- Run
yarn typecheck - Run
yarn test
If either fails, do not commit or push until the failure is fixed or clearly explained.
Runtime references
Useful references:
- Node compatibility:
https://developers.cloudflare.com/workers/runtime-apis/nodejs/ - Workers errors:
https://developers.cloudflare.com/workers/observability/errors/
SECURITY
- NEVER commit API keys.
- NEVER commit
.dev.vars. wrangler.jsonccontains Cloudflare account IDs (not secret but don't expose). If an ID gets added then interpolate it like this:
{
"binding": "TENANT_DB",
"database_name": "my-sandbox-tenant-db",
"database_id": "${TENANT_DB_ID}"
}
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.
- 2mo ago First seen · 80 lines · 427 tokens per session scan A 0bcc850b2aa3
agents-kanban AGENTS.md is an instructions file published in the GitHub repository abuiles/agents-kanban (13 stars, last pushed 8mo ago), licensed MIT. It adds 427 tokens to every session, about $0.0017 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 2026-08-30.
agents-kanban AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agents-kanban AGENTS.mdabuiles/agents-kanban | Instructions file | 13 | 8mo ago | MIT | A | 427 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |