Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add liza-mas/liza --skill checkpoint-summarygit clone --depth 1 https://github.com/liza-mas/lizaWrote 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/liza-mas/liza/checkpoint-summary)<a href="https://agentmods.dev/skills/liza-mas/liza/checkpoint-summary"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/checkpoint-summary/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/liza-mas/liza/checkpoint-summary"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/checkpoint-summary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.02440 |
| Opus 5 | $0.00010 | $0.01220 |
| Sonnet 5 | $0.00004 | $0.00488 |
| Haiku 4.5 | $0.00002 | $0.00244 |
Grade A, and why
checkpoint-summary 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
After agents complete a planning or writing phase (epic planning, story writing, spec generation), summarize their output so a human can efficiently review what was decided, what remains open, and where their attention is needed.
This skill answers: "What did the agents produce, what did they decide, and what do I need to weigh in on?"
The agents already did the work — planning, reviewing, approving. This skill reads their outputs and distills them into a checkpoint summary that respects the human's time.
Distinct from spec-review: spec-review audits spec quality. This skill summarizes what was already reviewed and approved, surfacing only what needs human judgment.
Trigger
Use this skill when:
- Epic planning completes and the human needs a checkpoint summary
- Story writing completes across multiple agents
- Any multi-agent phase produces artifacts the human hasn't read
- User asks "what did the agents produce?", "what needs my attention?", or "summarize the plans"
- Orchestrator requests a human checkpoint (§BRAND_NAME_TITLE§ mode)
Inputs
The single entry point is §BRAND_PROJECT_DIRNAME§/state.yaml — the source of truth for all §BRAND_NAME_TITLE§ state.
From state.yaml, the skill reads:
goal.spec_ref: the upstream source document the agents worked fromtasks[]: each task with its scope, status, output capabilities, approvals, and history- Artifact refs (read all that exist, in priority order):
tasks[].plan_ref/tasks[].arch_ref— task-level planning and architecture artifactstasks[].output[].plan_ref/tasks[].output[].arch_ref— output-entry artifactstasks[].spec_ref— task-level spec (may differ fromgoal.spec_ref)
tasks[].approvals[]: review verdicts with provider/diversity context (canonical); fall back totasks[].approved_byifapprovals[]is absenttasks[].history[]: full event timeline (claimed, checkpoint, submitted, approved, merged)sprint.statusandsprint.checkpoint_trigger: why the checkpoint was triggered
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 · 243 lines · 20 tokens per session scan A 180e049d0de9
checkpoint-summary is a skill published in the GitHub repository liza-mas/liza (382 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 2,440 once invoked, about $0.0001 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…