outlook-local-mcp: Skill for Claude Code

.agents/skills/checkpoint-read/SKILL.md

checkpoint-read is a skill for Claude Code, Codex from desek/outlook-local-mcp. It costs 36 tokens per session (563 once invoked), scanned A, original, MIT.

A command that reads checkpoint commits from Git history. These commits are saved progress notes describing completed work, remaining tasks, and important decisions.

In plain words
What is it for?
Use it at the start of a session to review the latest checkpoint commits and see what was implemented, what remains, and which decisions were recorded.
Why use it?
It restores context when starting a new coding session, so you do not have to reconstruct the project's recent history manually.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is desek/outlook-local-mcp's own configuration. It tells Claude Code and Codex how to work on outlook-local-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 outlook-local-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to desek/outlook-local-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/desek/outlook-local-mcp/main/.agents/skills/checkpoint-read/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/desek/outlook-local-mcp

Made for: Claude Code, Codex.

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 checkpoint-read

README.md
[![agentmods](https://agentmods.dev/badge/skills/desek/outlook-local-mcp/checkpoint-read/github.svg)](https://agentmods.dev/skills/desek/outlook-local-mcp/checkpoint-read)
Your own site
<a href="https://agentmods.dev/skills/desek/outlook-local-mcp/checkpoint-read"><img src="https://agentmods.dev/badge/skills/desek/outlook-local-mcp/checkpoint-read/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 checkpoint-read

Your own site · 80×15
<a href="https://agentmods.dev/skills/desek/outlook-local-mcp/checkpoint-read"><img src="https://agentmods.dev/badge/skills/desek/outlook-local-mcp/checkpoint-read.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 563 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 65
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
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 $0.00036 $0.00563
Opus 5 $0.00018 $0.00282
Sonnet 5 $0.00007 $0.00113
Haiku 4.5 $0.00004 $0.00056

Measured 9d ago against content hash 5bd2d7d06bbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

checkpoint-read 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 9d 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.

.agents/skills/checkpoint-read/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/checkpoint-read

Reads checkpoint commit history to recover project context when starting a new session. Queries Git history for checkpoint commits created by /checkpoint-commit, displays the most recent relevant checkpoint details, and summarizes what was implemented, what remains, and any decisions captured — enabling seamless session continuity.

Usage: /checkpoint-read

No arguments required. The command automatically reads the most recent checkpoint commits from local Git history.

Workflow

Follow these steps in order.

Step 1: List Recent Checkpoints

Query Git history for checkpoint commits:

git log --oneline --decorate --grep '^checkpoint.*:' -n 25
  • If no results: Report "No checkpoint commits found in this repository." and STOP. Proceed with the session without checkpoint context.
  • If results exist: Display the list of recent checkpoint commits to provide an overview of checkpoint history.

Step 2: Read Most Recent Checkpoint

Extract the SHA from the most recent (first) checkpoint in the list, then read its full details:

# Show commit stats (files changed)
git show --stat {SHA}

# Show full commit message and diff
git show {SHA}

Parse the commit message subject line and body for context recovery.

Step 3: Summarize Context

Analyze the checkpoint commit message and produce a structured summary with three sections:

  1. What was implemented: Extract completed work from the commit body bullet points and diff content.
  2. What remains: Identify pending items, TODOs, or incomplete work mentioned in the commit message.
  3. Decisions captured: Note any architectural or design decisions recorded in the commit message.

Step 4: Report

Present the structured summary to the user, including:

  • The checkpoint commit SHA and date for reference
  • The CR identifier from the commit subject (e.g., CR-XXXX)
  • The three-section context summary (implemented, remaining, decisions)

Safety Rules

Read the full file on GitHub · 69 lines

Files

What ships with it

2 files 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.

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. 9d ago First seen · 69 lines · 36 tokens per session scan A 5bd2d7d06bbc

Subscribe to this mod's changes

checkpoint-read is a skill published in the GitHub repository desek/outlook-local-mcp (41 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 563 once invoked, about $0.0002 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 2026-08-30.