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-distill/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-distill)<a href="https://agentmods.dev/skills/desek/outlook-local-mcp/checkpoint-distill"><img src="https://agentmods.dev/badge/skills/desek/outlook-local-mcp/checkpoint-distill/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-distill"><img src="https://agentmods.dev/badge/skills/desek/outlook-local-mcp/checkpoint-distill.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 172 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 Memory Poisoning · line 132 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00079 | $0.04009 |
| Opus 5 | $0.00039 | $0.02005 |
| Sonnet 5 | $0.00016 | $0.00802 |
| Haiku 4.5 | $0.00008 | $0.00401 |
Grade A, and why
checkpoint-distill 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/checkpoint-distill
Turns the artifacts of finished work into standing guidance a future session inherits. A coding agent is episodic: each session begins without the context of the last one — what was tried, what failed, what stuck, and why. Standing instructions carry that across the gap, but only if something deliberately puts the knowledge there. This skill reads the durable record a unit of work leaves behind, extracts the constraints, failure narratives, and foot-guns worth keeping, ranks them, and — on explicit per-tier approval — writes them into the project's standing instructions as narrative rather than as a list of bare rules.
A bare rule does not survive contact with inconvenience: "do X" tells a future reader what, not why, so the first time the constraint is awkward it gets stripped as arbitrary. The reasoning is the load-bearing part. That is why this skill writes narrative carrying the mechanism, the cost, and the history behind each rule, never a stripped constraint.
Usage:
| Invocation | Scope |
|---|---|
/checkpoint-distill CR-XXXX |
Change Request scoped: analyses that Change Request's durable artifacts. This is the default mode. |
/checkpoint-distill --branch |
Branch scoped: analyses the current branch's commits, delimited by the merge base with the default branch. |
Both scopes name a semantic unit of work. There is deliberately no mode that analyses an arbitrary count of most-recent commits: a commit count is neither a semantically bounded unit nor stable across a merge, so a window of N commits silently changes meaning the moment history is squashed. If a scope is not supplied and cannot be resolved, the skill asks rather than inventing a commit window.
Invocation Contract
The two scopes above are the only two the skill accepts. Everything below constrains how they behave.
Change Request scope is the default
Invoked with a Change Request identifier and no other argument, the skill scopes the entire analysis to that Change Request's artifacts. It bounds the work by the unit the identifier names, never by a count of recent commits. Change Request scope is the default because it is the scope whose material survives a squash merge: the tracked documents a Change Request leaves behind persist unchanged through the merge, whereas commit-borne reasoning does not.
What ships with it
5 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.
- 11d ago First seen · 200 lines · 79 tokens per session scan A ec5e8e7337fa
checkpoint-distill is a skill published in the GitHub repository desek/outlook-local-mcp (41 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 4,009 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.