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.
curl -O https://raw.githubusercontent.com/desek/outlook-local-mcp/main/.agents/skills/checkpoint-iterate/SKILL.mdgit clone --depth 1 https://github.com/desek/outlook-local-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/desek/outlook-local-mcp/checkpoint-iterate)<a href="https://agentmods.dev/skills/desek/outlook-local-mcp/checkpoint-iterate"><img src="https://agentmods.dev/badge/skills/desek/outlook-local-mcp/checkpoint-iterate/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/desek/outlook-local-mcp/checkpoint-iterate"><img src="https://agentmods.dev/badge/skills/desek/outlook-local-mcp/checkpoint-iterate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 139 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.
- medium Excessive Agency · line 52 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00091 | $0.02710 |
| Opus 5 | $0.00046 | $0.01355 |
| Sonnet 5 | $0.00018 | $0.00542 |
| Haiku 4.5 | $0.00009 | $0.00271 |
Grade A, and why
checkpoint-iterate 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 10d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/checkpoint-iterate
Runs an iteration session that closes the last-mile gap between an implemented Change Request and the behaviour that was actually wanted. A specification is written before the code exists, so the delivered result is approximately right rather than exactly right. Closing that gap is an interactive loop: the user names what to try, the agent makes the change and reports the evidence, the user renders the verdict. This skill records that loop in a ledger at docs/cr/{CR_ID}-iterate.md, so the reasoning — including every discarded attempt — survives the session instead of evaporating with the agent's context.
Usage:
| Invocation | Effect |
|---|---|
/checkpoint-iterate CR-XXXX |
Opens a session against that Change Request, or resumes one already open |
/checkpoint-iterate close CR-XXXX |
Closes the active session and distils the ledger |
/checkpoint-iterate status CR-XXXX |
Reports the active session, its attempt count, and its dispositions so far |
Every invocation MUST identify its governing Change Request. There is no implicit "current session".
Role Split
The division of labour governs every step below. It is fixed and MUST NOT be reassigned.
- The user initiates the session, names each thing to try next, and renders the verdict on each result. The verdict is the user's judgment; the agent records it and MUST NOT infer, assume, propose, or substitute its own.
- The agent makes the code change, runs the project's checks, reports the evidence, then writes the ledger entry and creates the commit. The agent is the recorder for every attempt, because it is the party present at all of them and already writing to the repository.
The user is therefore never asked to maintain a notebook alongside the work. Their contribution is direction and judgment; the recording is a side effect of the work the agent was already doing.
Initiation is user-only. A session MUST be opened by explicit user invocation. It MUST NOT be started automatically, and MUST NOT be spawned by the implementation pipeline. The whole point is that a human has looked at the delivered result and judged it not yet right.
What ships with it
3 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.
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.
- 10d ago First seen · 143 lines · 91 tokens per session scan A a8134510a5c7
checkpoint-iterate is a skill published in the GitHub repository desek/outlook-local-mcp (41 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 2,710 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…