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 jscraik/Agent-Skills --skill alignment-checkpointgit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/jscraik/agent-skills/alignment-checkpoint)<a href="https://agentmods.dev/skills/jscraik/agent-skills/alignment-checkpoint"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/alignment-checkpoint/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/jscraik/agent-skills/alignment-checkpoint"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/alignment-checkpoint.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 | $0.00043 | $0.00705 |
| Opus 5.5 | $0.00017 | $0.00282 |
| Sonnet 5.5 | $0.00009 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
alignment-checkpoint 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 1mo 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alignment Checkpoint
When To Use
- The user explicitly requests a checkpoint before action.
- An unresolved decision materially changes scope, risk, or authority.
- Do not activate merely because a task is high-stakes or has multiple steps. Use proportionate verification for a clear, authorized task instead.
Inputs
- User request, target, constraints, and existing authorization.
- The unresolved decision and its consequences, if a decision is missing.
- An explicit tool hold, if the user requested one.
Outputs
- A concise statement of the goal, assumptions, and success criteria.
- The one material question or decision and the action waiting on it.
- An explicit approval boundary; schema-bound outputs include
schema_version.
Workflow
- Identify the requested checkpoint or material unresolved decision.
- Inspect only relevant read-only evidence unless the user prohibited tools.
- State the decision and consequences; ask only what changes scope, risk, or authority. Do not ask for duplicate approval of an existing bounded request.
- Hold only the affected action. Continue independent authorized work.
- Finish the checkpoint when its decision and waiting action are clear. Continue implementation only under the authority actually granted.
Failure Mode
- If the user says no tools, return the checkpoint without invoking tools.
- If evidence is unavailable, state the uncertainty and ask the necessary question; do not manufacture a failing gate or begin unrelated repair work.
- A blocked deployment or production decision does not block independent local inspection or tests unless the user explicitly requires a full pause.
Validation
- Fail fast: stop at the first failed gate; do not proceed with the affected action until its required check passes. Independent authorized work remains in scope.
- Check that the output names the unresolved decision and the affected action.
- Confirm that existing authorization was preserved and no prohibited action occurred.
- When this skill changes, run the owning strict skill audit, package check, and focused positive/negative eval cases. Report exact pass, fail, or blocked command outcomes; do not run product validation merely to return a checkpoint.
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.
- 1mo ago Changed · +9 lines · +7 tokens per session 1f54739aeddd
- 1mo ago First seen · 73 lines · 36 tokens per session scan A 45ad1e393171
alignment-checkpoint is a skill published in the GitHub repository jscraik/Agent-Skills (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 43 tokens to every session and 705 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
agui-dotnet-streaming-chat
Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…