Borrowing it
Nothing to install: this file belongs to LeoPhoenixT/readNdraft-imap-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/LeoPhoenixT/readNdraft-imap-mcp/main/.agents/skills/readndraft-local-mcp-test/SKILL.mdgit clone --depth 1 https://github.com/LeoPhoenixT/readNdraft-imap-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/skills/leophoenixt/readndraft-imap-mcp/readndraft-local-mcp-test)<a href="https://agentmods.dev/skills/leophoenixt/readndraft-imap-mcp/readndraft-local-mcp-test"><img src="https://agentmods.dev/badge/skills/leophoenixt/readndraft-imap-mcp/readndraft-local-mcp-test/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/skills/leophoenixt/readndraft-imap-mcp/readndraft-local-mcp-test"><img src="https://agentmods.dev/badge/skills/leophoenixt/readndraft-imap-mcp/readndraft-local-mcp-test.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 | $0.00086 | $0.01233 |
| Opus 5 | $0.00043 | $0.00616 |
| Sonnet 5 | $0.00017 | $0.00247 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
readndraft-local-mcp-test 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 11d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test the readNdraft Local MCP
Run this workflow only from the readNdraft repository root.
Preserve local work
- Inspect
git status -sbbefore running anything. - Treat modified and untracked files as user-owned. The test workflow must not stage, reset, delete, or rewrite them.
- Confirm
.codex/config.tomldefinesmcp_servers.readndraft_devand launches the checkout through lockeduvwithrequired = falsefor ordinary work.
Confirm the repository configuration
Use this repository-scoped configuration:
[mcp_servers.readndraft_dev]
command = "uv"
args = ["run", "--locked", "--no-sync", "readndraft-imap-mcp", "mcp"]
cwd = "."
startup_timeout_sec = 10
tool_timeout_sec = 60
required = false
default_tools_approval_mode = "approve"
Run Codex with codex -C . from the repository root; MCP cwd is resolved from
that Codex working directory, so use cwd = ".". Confirm the resolved entry
with codex -C . mcp get readndraft_dev --json; do not edit the user's global
Codex configuration. If a required MCP session closes during initialization,
inspect the resolved cwd first and temporarily pin it to the absolute
repository root to distinguish a path problem from a server problem.
Refresh changed local code
Do not rebuild or reinstall for ordinary Python source edits. uv run executes
this checkout. Run uv sync --locked --extra dev only when the environment is
missing, unsynchronized, or dependency/lock metadata changed.
Distinguish the two processes before testing:
- A new Codex CLI session starts a fresh MCP frontend from the checkout.
- The frontend reuses any healthy broker at the current IPC protocol endpoint.
- Therefore, frontend-only changes are picked up by a new CLI session, but
broker-side changes under
broker/,imap/,mime/,drafts/, or shared code require a fresh broker process.
Before refreshing the broker, close or disconnect active readNdraft MCP
frontends when practical so their leases end. On Windows, inspect only processes
whose command line contains readndraft_imap_mcp.broker.daemon; do not stop a
process based only on python.exe. Show the exact PID, executable, and command
line, explain that connected clients will briefly lose readNdraft access, and
obtain direct user confirmation before stopping that exact process. Never stop
unrelated Python or Codex processes.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 125 lines · 86 tokens per session scan A 809ea1e3bd1a
readndraft-local-mcp-test is a skill published in the GitHub repository LeoPhoenixT/readNdraft-imap-mcp (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 86 tokens to every session and 1,233 once invoked, about $0.0004 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.
Other skills, from other repositories
safe-email-operations
Use email through the bundled mcp-email-server MCP server, diagnose bounded non-secret state, and hand account or credential setup to a user-operated CLI or authenticated local UI.
coordinate
Kick off a multi-agent coordination task. Sends one email thread that CC's the whole team and lets them take turns.
octave-compression
Workflow for transforming prose into semantic OCTAVE structures. Covers tier selection, transformation phases, loss accounting, and decision rules. REQUIRES octave-literacy.
create-agent
Create a new AgenticMail agent with a name and a role, ready to coordinate with others over email.
style-guide
Dedalus style guide quick reference. Key rules for writing code that lasts. Use when writing or reviewing Python code.
scrape-batch
Extract many known URLs in one polite, rate-limited pass. Use when the user hands over a list of links, a set of search hits to read in full, or asks to "scrape these pages" / "pull the content from all of them". Drives extract(action="batch"), which fans out with per-domain rate limiting and returns partial results…