What is modal-mcp AGENTS.md?

A repository instruction file for a local, read-only connector that lets agents inspect Modal state, where Modal is a platform for running workloads in the cloud.

Running the project’s tests, checks, diagnostics, and local server workflows while maintaining its security and approval rules.

It keeps the agent within project rules: use the managed environment, protect credentials, preserve read-only behavior, and leave merges and releases to a human.

modal-mcp AGENTS.md — Instructions file by php-workx

Install

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.

agentmods

npx agentmods add instructions/php-workx/modal-mcp/agents-md

Clone the repo

git clone --depth 1 https://github.com/php-workx/modal-mcp

Made for: Codex, OpenCode.

Per session 385 This file is loaded in full into every session.

When invoked 385 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00385	$0.00385
Opus 5	$0.00192	$0.00192
Sonnet 5	$0.00077	$0.00077
Haiku 4.5	$0.00038	$0.00038

Measured yesterday against content hash 2852eee99770, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

modal-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 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.

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.

AGENTS.md · 58 lines

What it actually says

AGENTS.md

AGENTS.md is the durable instruction file for this repo.

What This Repo Is

modal-mcp is a local, read-oriented MCP server for inspecting Modal state. The core product boundary is that credentials stay local and the default tool surface is read-only.

Hard Rules

Preserve the read-only default posture unless a task explicitly asks for mutating behavior.
Never check real Modal credentials or secrets into the repo.
Prefer the repo’s uv-managed Python environment over ambient Python.
Keep local-file secret handling and .env-driven setup intact.
Never merge pull requests or create releases without explicit user approval. Agents may prepare, review, and push changes, but the human must trigger merges, releases, and any action that modifies the default branch.

Common Commands

uv sync --extra dev
uv run pytest
uv run ruff check .
uv run modal-mcp doctor --env-file .env
uv run modal-mcp run --env-file .env

Optional stricter checks if needed:

uv run mypy src
uv run pip-audit

Common Workflows

1. Server or tool changes

Run tests and lint through uv.
Preserve the read-oriented tool contract unless the task explicitly changes that product decision.
Keep setup and doctor flows working for local users.

2. Credential or setup changes

Do not replace file-based secret handling with checked-in secrets.
Keep .env and .secrets/ semantics local-only.
If setup behavior changes, update the README examples too.

References

README.md — product boundaries and setup flow
pyproject.toml — runtime and dev-tool entry points

Changes

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 · 58 lines · 385 tokens per session scan A 2852eee99770

Subscribe to this mod's changes

modal-mcp AGENTS.md is an instructions file published in the GitHub repository php-workx/modal-mcp (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 385 tokens to every session, about $0.0019 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 2026-08-31.

Debugging Security Testing

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

modal-mcp AGENTS.md