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/scanmalware/mcp-server/agents-mdgit clone --depth 1 https://github.com/scanmalware/mcp-serverWhat 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 | $0.01550 | $0.01550 |
| Opus 5 | $0.00775 | $0.00775 |
| Sonnet 5 | $0.00310 | $0.00310 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
mcp-server AGENTS.md scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Other “download” style endpoints may be binary (verify with `curl -D - -o /dev/null ...`). How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repo will contain a Python Model Context Protocol (MCP) server that exposes the ScanMalware.com API as tools/resources for an MCP client.
API source of truth
- OpenAPI spec:
https://scanmalware.com/openapi.json - Base URL (OpenAPI omits
servers):https://scanmalware.com - API prefix:
/api/v1 - OpenAPI currently lists ~146 paths / ~147 operations; many response schemas are
{}(treat as untyped JSON and verify with live calls).
Practical note: some endpoints return binary despite the OpenAPI describing JSON:
GET /api/v1/screenshot/{scan_id}returns PNG bytes.GET /api/v1/tls/{scan_id}/certificate/downloadreturns PEM (application/x-pem-file).- Other “download” style endpoints may be binary (verify with
curl -D - -o /dev/null ...).
Authentication
Most endpoints are public (no auth in OpenAPI). Auth-gated endpoints in the spec:
- Bearer (
HTTPBearer)GET /api/v1/auth/profileGET /api/v1/auth/adminGET /api/v1/auth/analyst
- Optional bearer (
OptionalHTTPBearer)GET /api/v1/auth/test-optional
- HTTP Basic (
HTTPBasic) (Module Monitoring)GET /api/v1/modules/healthGET /api/v1/modules/statsGET /api/v1/modules/failuresGET /api/v1/modules/stuckGET /api/v1/modules/chainsGET /api/v1/modules/scan/{scan_id}GET /api/v1/modules/percentiles/{module_name}POST /api/v1/modules/admin/change-password
Recommended env vars (never hardcode secrets):
SCANMALWARE_BASE_URL(default:https://scanmalware.com)SCANMALWARE_BEARER_TOKEN(optional; only needed for auth endpoints)SCANMALWARE_BASIC_USER/SCANMALWARE_BASIC_PASSWORD(optional; only needed for/modules/*)
Core scan workflow (API-level)
POST /api/v1/scanwith JSON body:url(required)scan_type(default"public")options(object, optional)- Optional headers:
User-Agent
- Poll for completion:
GET /api/v1/scan/{scan_id}/summary(compact; includesstatus,risk_score, counts)- and/or
GET /api/v1/result/{scan_id}/progress
- Fetch details:
GET /api/v1/result/{scan_id}- plus specialized endpoints (
/ai/{scan_id},/tls/{scan_id},/technologies/by-scan/{scan_id}, etc.)
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.
- yesterday First seen · 125 lines · 1,550 tokens per session scan A b28e9ddbe126
mcp-server AGENTS.md is an instructions file published in the GitHub repository scanmalware/mcp-server (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 1,550 tokens to every session, about $0.0077 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.