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 adonai-labs/agent-runway --skill checkpointgit clone --depth 1 https://github.com/adonai-labs/agent-runwayWrote 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/adonai-labs/agent-runway/checkpoint)<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/checkpoint"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/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/adonai-labs/agent-runway/checkpoint"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/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 | $0.00053 | $0.00604 |
| Opus 5 | $0.00026 | $0.00302 |
| Sonnet 5 | $0.00011 | $0.00121 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
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 8d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkpoint
Invoke Skill
@checkpoint [optional title or mode]
Examples:
@checkpoint@checkpoint before refactor@checkpoint handoff
What this skill does
Creates a compact, factual snapshot of the current work state.
Use it when work is paused, switching context, handing off to another agent, or preserving a useful point during rapid iteration.
Workflow
1. Inspect current state
Gather only observable context:
- current branch and git status, if available
- recently changed files
- current task intent
- completed changes
- validation already run
- known risks, blockers, or open questions
- the most useful next command or file to inspect
Do not invent completed work. If something was not validated, say so.
2. Choose checkpoint mode
Default mode is short.
Use handoff mode when the developer says handoff, handover, resume later, or explicitly asks for another agent/person to continue.
| Mode | Use when | Length |
|---|---|---|
| Short | Pausing or marking progress | About 20-40 lines |
| Handoff | Another session/person must continue | Detailed enough to resume safely |
3. Write the checkpoint
If filesystem write access is available, create:
.agent-runway/logs/checkpoints/YYYY-MM-DD-HHMM-<slug>.md
Use the local date/time when available. If the task has no clear title, use checkpoint as the slug.
If filesystem writes are not available, return the checkpoint content in chat and say it was not written to disk.
4. Use this template
# Checkpoint: <title>
Date: <local date/time>
Branch: <branch or unknown>
Status: <clean/dirty/unknown>
## Intent
<What the work is trying to accomplish.>
## Current State
<What is true right now. Mention changed files when useful.>
## Changes Made
- <Observed completed change>
## Validation
- <Command/result, or "Not run">
## Open Threads
- <Open question, risk, or blocker>
## Resume From Here
<The next concrete action.>
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.
- 8d ago First seen · 112 lines · 53 tokens per session scan A f49575a2f201
checkpoint is a skill published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 19d ago), licensed MIT. It adds 53 tokens to every session and 604 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
pr-blocker-summarizer
Summarizes open pull requests into a blockers-first standup digest. Activates when the user asks to summarize open PRs, find blocked pull requests, generate a PR standup, or triage review backlog from a PR export.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
full-audit
Exhaustive, denominator-driven audit of an entire area (codebase, docs, memory, skills, DB, config). Runs a 6-phase pipeline: scope agreement + prior-map diff -> deterministic sweep (counts/versions/paths/parsing plus cross-index reconciliation) -> parallel read-only content review (citations forced, rule dry-run) ->…
tech-lead/code-review
A checklist-based method for examining code for correctness, security, performance, clarity, and ease of maintenance.