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 agentmods add skills/yanfeid/claude-amber/checkpointnpx skills add yanfeid/claude-amber --skill checkpointgit clone --depth 1 https://github.com/yanfeid/claude-amberWrote 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/yanfeid/claude-amber/checkpoint)<a href="https://agentmods.dev/skills/yanfeid/claude-amber/checkpoint"><img src="https://agentmods.dev/badge/skills/yanfeid/claude-amber/checkpoint.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.00430 |
| Opus 5 | $0.00031 | $0.00215 |
| Sonnet 5 | $0.00012 | $0.00086 |
| Haiku 4.5 | $0.00006 | $0.00043 |
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 5d 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.
What it actually says
/amber:checkpoint — seal your working state
Write everything a fresh instance of you would need to continue this work, to .amber/STATE.md (overwrite; create .amber/ if needed).
Additional instruction from user (may be empty): $ARGUMENTS
What to write
Use exactly this structure:
# Working state
Sealed: <ISO datetime>
## Task
<What we are doing and WHY — one short paragraph. Include who asked and what done looks like.>
## Decisions made (do not re-litigate)
- <decision> — <one-line reason>
## Current status
<Where the work stands right now. What is verified working, what is untested.>
## Files in play
- <path> — <what changed / why it matters>
## Open problems / gotchas
- <Anything that bit you: failing test + suspected cause, weird constraint, thing the user corrected you on>
## Next steps
1. <Concrete next action, specific enough to execute without re-reading the whole conversation>
Rules
- Write for an amnesiac: assume the reader has NOT seen this conversation. No "as discussed above", no shorthand labels you invented mid-session.
- Record why, not just what — the reasoning is exactly what compaction destroys.
- Mid-debug? The error message, what you tried, and your current hypothesis are the most valuable lines in the file. Never omit them.
- Budget: under 60 lines. Drop anything derivable from the code or git history.
- Do not put secrets, API keys, or tokens in this file.
After writing, tell the user in one sentence that state is sealed and will auto-restore after compaction or in the next session.
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.
- 5d ago First seen · 47 lines · 62 tokens per session scan A 15552a6ce62b
checkpoint is a skill published in the GitHub repository yanfeid/claude-amber (2 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 430 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
setup
Scaffold the handoff project-memory system into THIS repository (new or existing) — copies the template tree into .handoff/, then runs a guided discovery pass that drafts a real STATUS, MAP, TECHSTACK, and PRODUCT from the actual codebase and confirms with the user before saving. Use when the user says "set up…
wire-memory
ALWAYS USE THIS SKILL. Automatic context logging and retrieval via Wire container. Invoke this skill at the start of every session, when making decisions, when receiving corrections, when establishing patterns, and before ending sessions. This skill provides persistent cross-project memory that supplements the…
wire-configure
Configure Wire memory settings (transcript capture, etc.).
wire-connect
Connect Wire memory to this agent. Authenticates via browser and registers your Wire container's MCP tools.
wire-claim
Claim an ephemeral Wire memory container to make it permanent. Opens a browser to create an account.
omega-memory
Persistent memory for AI coding agents. Teaches agents how to use OMEGA's MCP tools for storing decisions, querying context, coordinating multi-agent workflows, and resuming tasks across sessions.