Borrowing it
Nothing to install: this file belongs to sankaHQ/sanka-mcp. 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/sankaHQ/sanka-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/sankaHQ/sanka-mcpWrote 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/sankahq/sanka-mcp/agents-md)<a href="https://agentmods.dev/instructions/sankahq/sanka-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sankahq/sanka-mcp/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/sankahq/sanka-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sankahq/sanka-mcp/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 | $0.00569 | $0.00569 |
| Opus 5.5 | $0.00228 | $0.00228 |
| Sonnet 5.5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
sanka-mcp 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 1mo 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sanka-mcp
The hosted Sanka MCP server (packages/mcp-server/) and the TypeScript client it
uses to call the Sanka API (src/). Read CONTRIBUTING.md for setup, the
repository model, tests and linting. Workspace-wide rules live in the
sanka-project workspace AGENTS.md; AI-authored changes use the workspace
sanka-pr-flow.
Tests
Follow the workspace test-audit skill.
- Before adding a test, state in the PR which failure it catches (for new behaviour: the specified behaviour not holding) and why no existing test at a stronger boundary already catches it. Tests for new behaviour go at the single boundary that owns it; a test that cannot name a failure is not added.
- One owner per behaviour. A tool test asserts the outgoing HTTP request and the
tool result for a given response (see
tests/mcp-server/mutation-passthrough-v2.test.ts), not that an SDK mock was called. Route behaviour is owned bysanka-api; do not re-test it here. - Never write a test that reads source, doc or config files as text and asserts
on the text; pins descriptions, schema metadata or other literals that are not
a public contract; only asserts that a mock was called; asserts
toBeDefined/typeof; asserts that a tool is registered; or computes the expected value with the code under test. - Documented compatibility contracts are the exception to the literal rule: tool names and input schemas that are published to clients, error codes and retained URLs are asserted exactly, once, at their owning boundary.
- Do not write unit tests after the code to cover a diff. A regression test must fail on the pre-fix code; say so in the PR.
- Test lines added in a PR may not exceed non-test lines added unless the PR explains why (bug reproduction, new pure module, table-driven cases).
- Extend a table or
test.eachrow instead of copying a test. Split or trim a test file above 1,500 lines before adding anything to it. - Fix a test slower than 0.5 s. Never add sleeps, real timers or real network waits.
- When a behaviour-preserving refactor breaks tests, delete or rewrite them at the owning boundary. Do not edit assertions to match the new implementation.
- No meta-tests that require other tests, docs listings or registrations to exist.
- Deleting a low-value test is a valid change on its own. Report test and non-test line counts separately in the PR.
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.
- 1mo ago First seen · 42 lines · 569 tokens per session scan A d6754d7a58eb
sanka-mcp AGENTS.md is an instructions file published in the GitHub repository sankaHQ/sanka-mcp (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 569 tokens to every session, about $0.0023 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 2026-09-26.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.