proton-bridge-mcp: Instructions file for Codex

AGENTS.md

proton-bridge-mcp AGENTS.md is an instructions file for Codex, OpenCode from Considus/proton-bridge-mcp. It costs 1,030 tokens per session, scanned B, original, Apache-2.0.

Repository instructions for a server that handles email through Proton Bridge. They require work to be isolated on a Git branch, built, checked with evidence, and shipped in a pull request.

In plain words
What is it for?
Use them when changing the email server to choose a safe branch, inspect project rules, build the code, prove it works, and prepare a focused pull request.
Why use it?
They reduce the risk of changing the wrong branch, overlapping with existing work, or accidentally staging private email and local state files. They make the development steps explicit before changes are submitted.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is Considus/proton-bridge-mcp's own configuration. It tells Codex and OpenCode how to work on proton-bridge-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything proton-bridge-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Considus/proton-bridge-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.

Copy the file
curl -O https://raw.githubusercontent.com/Considus/proton-bridge-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Considus/proton-bridge-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for proton-bridge-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/considus/proton-bridge-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/considus/proton-bridge-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/considus/proton-bridge-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/considus/proton-bridge-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.

agentmods 80×15 button for proton-bridge-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/considus/proton-bridge-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/considus/proton-bridge-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,030 This file is loaded in full into every session.
When invoked 1,030 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01030 $0.01030
Opus 5.5 $0.00412 $0.00412
Sonnet 5.5 $0.00206 $0.00206
Haiku 4.5 $0.00103 $0.00103

Measured 13d ago against content hash d3b80afe0269, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

proton-bridge-mcp AGENTS.md scanned grade B 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 13d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

for h in pre-commit commit-msg; do git show "origin/main:hooks/$h" > "$d/$h.tmp" && chmod 755 "$d/$h.tmp" && mv "$d/$h.tmp" "$d/$h" || { rm -f "$d/$h.tmp"; echo "not copied: $h"; }; done
AGENTS.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent notes

For a coding agent working in this repo. People start with CONTRIBUTING.md; this file does not repeat it. The server handles somebody's email, so it is deliberately boring.

Build

  • Keep the ground rules in CONTRIBUTING.md: standard library only, assume the mail is hostile, small diffs. Think hardest where a change lets message content reach a decision, a file path, a recipient or a tool argument.
  • Hard-delete nothing (Trash is the furthest), delete no folder, and keep sending, forwarding, replying and the bulk mutations behind the confirmation gate. draft=true is ungated on purpose. README.md gives the reasons.
  • Keep attachment writes inside the allowed directories. Widening that set is the user's decision, never reachable from something an email said: reading any file and posting it out is how data walks off a computer.
  • Keep Python 3.9 working. CI runs 3.9 and 3.12. A 3.10-only construct (match, a runtime-evaluated X | Y annotation, zip(strict=), itertools.pairwise, tomllib, dataclass(slots=)) fails only in the 3.9 leg.
  • Change the version and the tool list in server.py, then run ./build-mcpb.py --sync. manifest.json is generated; tool titles, hints and the read-only classification are in CONTRIBUTING.md ("Building the bundle").

Conversations are not messages. The Proton web UI groups a thread into one row; IMAP hands back the individual messages. A count that looks wrong is usually this.

Test

python3 -m compileall -q server.py setup.py tests
python3 -m unittest discover -s tests -v
./build-mcpb.py --check

A PR needs all three green. Read the test count, not the word "passed".

Capture the before while reproducing and the after once it works, usually as a pair of command outputs. Never paste real mail, a real address or a real attachment into a PR, an issue or a test fixture.

Not checkable without a real account: anything that talks to Bridge over IMAP or SMTP, UIDVALIDITY across a Bridge restart, how Proton's server-side filters interact (Bridge cannot see them), and send and forward end to end.

Read the full file on GitHub · 52 lines

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.

  1. 13d ago Changed · +64 tokens per session d3b80afe0269
  2. 19d ago Changed · +9 lines · +210 tokens per session scan A → B 62b9480d551a
  3. 20d ago Changed · -21 lines · -645 tokens per session b7480b5228fd
  4. 1mo ago Changed · +2 lines · +46 tokens per session 16cf150253dd
  5. 1mo ago Changed · +10 tokens per session 03a429a5f0d0
  6. 1mo ago Changed · +5 tokens per session 6604f6f51259
  7. 1mo ago Changed · +37 tokens per session 1ffd34f033dd
  8. 1mo ago Changed · +46 tokens per session f814cb962b46
  9. 1mo ago First seen · 62 lines · 1,257 tokens per session scan A 86ad9e685e54

Subscribe to this mod's changes

proton-bridge-mcp AGENTS.md is an instructions file published in the GitHub repository Considus/proton-bridge-mcp (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,030 tokens to every session, about $0.0041 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-18.

Related

proton-bridge-mcp AGENTS.md compared with instructions from other repositories

proton-bridge-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
proton-bridge-mcp AGENTS.mdConsidus/proton-bridge-mcpInstructions file1yesterdayApache-2.0B1,030Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode