Borrowing it
Nothing to install: this file belongs to o-sokhan/abm-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/o-sokhan/abm-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/o-sokhan/abm-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/o-sokhan/abm-mcp/agents-md)<a href="https://agentmods.dev/instructions/o-sokhan/abm-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/o-sokhan/abm-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/o-sokhan/abm-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/o-sokhan/abm-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 | $0.00386 | $0.00386 |
| Opus 5.5 | $0.00154 | $0.00154 |
| Sonnet 5.5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
abm-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 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
Guidance for AI coding agents (and humans) working in this repository.
What this is
A read-only FastMCP server wrapping the Apple School & Business Manager API.
abm_client.py handles auth (ES256 client-assertion JWT -> OAuth2 bearer token)
and HTTP (get, get_paginated). server.py exposes one @mcp.tool per
documented read operation.
Hard rules
- Read-only. Do not add write operations or
post/patch/deletemethods. - Paths come from Apple's docs, never guessed: https://developer.apple.com/documentation/applebusinessapi
- Never commit secrets.
.env,*.pem,*.p8, token files are gitignored. - Keep the smoke test green.
python test_smoke.pymust pass in every commit; it fails if any tool name starts with a write verb.
Auth gotchas (already handled — don't regress)
- JWT
aud=https://account.apple.com/auth/oauth2/v2/token(with/v2/), but the token POST goes to the non-v2URL. Mismatch ->invalid_client. - The Apple private key is SEC1 with explicit EC parameters; convert to
named-curve PKCS#8 (
openssl pkcs8 -topk8) before it will load.
Adding a tool
- Confirm method + path in Apple's docs.
- Add a thin
@mcp.toolcalling_get_client().get(...)/get_paginated(...)wrapped in_handle(...). - Add the tool name to
READ_TOOLSintest_smoke.py. - Run
python test_smoke.pyandruff check ..
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 · 35 lines · 386 tokens per session scan A 507eb65e37ed
abm-mcp AGENTS.md is an instructions file published in the GitHub repository o-sokhan/abm-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 386 tokens to every session, about $0.0015 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 2026-08-31.
abm-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| abm-mcp AGENTS.mdo-sokhan/abm-mcp | Instructions file | 0 | 3mo ago | MIT | A | 386 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |