session-checkpoint

A command for saving a small snapshot of the current work session before stepping away temporarily. It replaces the next-session notes with a minimal handoff and records newly crossed irreversible boundaries.

In plain words
What is it for?
Use it during a short break or pause in an ongoing coding-agent session.
Why use it?
It preserves enough context to resume later without creating a full end-of-day handoff. It also highlights actions that may be difficult to undo.

Command

Install

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.

agentmods
npx agentmods add commands/akshayrao14/git-practices/session-checkpoint
Clone the repo
git clone --depth 1 https://github.com/akshayrao14/git-practices
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 103 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00103
Opus 5 $0.00015 $0.00051
Sonnet 5 $0.00006 $0.00021
Haiku 4.5 $0.00003 $0.00010

Measured 2d ago against content hash 231b46cdb7f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-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 2d 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.

skills/session-loop/commands/session-checkpoint.md · 8 lines

What it actually says

Invoke the session-loop skill with focus=checkpoint. Load sub/checkpoint.md from the skill directory and follow it exactly.

Lighter than /session-wrap. Use when stepping away for an hour or two, not stopping for the day. Does not append to UPDATES.md, does not append to ledger, does not commit.

Changes

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.

  1. 2d ago First seen · 8 lines · 30 tokens per session scan A 231b46cdb7f9

Subscribe to this mod's changes

session-checkpoint is a command published in the GitHub repository akshayrao14/git-practices (0 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 103 once invoked, about $0.0002 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.