snapshot

snapshot is a command for coding agents from betmoar/cc-reload-plugin. It costs 22 tokens per session (552 once invoked), scanned A, original, MIT.

A session-saving command that writes a short summary to `.reload/session.md` and prepares it to be restored after `/clear` or `/compact`. These commands reset or shorten the conversation context.

In plain words
What is it for?
Use it before a context reset to save the session’s progress and automatically reload that summary afterward. It does not act when a separate `/repete` loop owns continuity.
Why use it?
It helps preserve the current work when the conversation context is reset, while keeping the saved session state out of the project’s Git history.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the cc-reload plugin — 1 skill, 3 commands, 4 hooks shipped together

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/betmoar/cc-reload-plugin/snapshot
Clone the repo
git clone --depth 1 https://github.com/betmoar/cc-reload-plugin

Or install cc-reload, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 4 hooks.

Wrote 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.

agentmods badge for snapshot

README.md
[![agentmods](https://agentmods.dev/badge/commands/betmoar/cc-reload-plugin/snapshot.svg)](https://agentmods.dev/commands/betmoar/cc-reload-plugin/snapshot)
Your own site
<a href="https://agentmods.dev/commands/betmoar/cc-reload-plugin/snapshot"><img src="https://agentmods.dev/badge/commands/betmoar/cc-reload-plugin/snapshot.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 552 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 $0.00022 $0.00552
Opus 5 $0.00011 $0.00276
Sonnet 5 $0.00004 $0.00110
Haiku 4.5 $0.00002 $0.00055

Measured 4d ago against content hash 09a5e02d4666, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

snapshot 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 4d 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.

commands/snapshot.md · 38 lines

What it actually says

Snapshot this session

Write a fresh session digest so the working thread survives a context reset, and arm cc-reload to rehydrate it automatically on the next /clear or /compact.

User note (optional): $ARGUMENTS

If a cc-repete loop is active (.repete/loop.local.md has active: true), STOP — cc-repete owns continuity here; tell the user to use /repete-continue instead and do nothing.

Otherwise:

  1. Create .reload/ if it does not exist, and if .reload/.gitignore is missing write it with a single line * (so this per-session state is never committed to the user's project).
  2. Check for a concurrent session before overwriting: bash "${CLAUDE_PLUGIN_ROOT}/scripts/claim-digest.sh" "$CLAUDE_CODE_SESSION_ID" If it prints a warning, relay it verbatim — another session owns the current digest and it has been saved aside. Never skip the write because of this; the incumbent is already preserved.
  3. Write .reload/session.md (overwrite), tight — under ~30 lines — using the template shape from ${CLAUDE_PLUGIN_ROOT}/templates/session.md:
    • frontmatter: session_id — run: echo "$CLAUDE_CODE_SESSION_ID" — paste that value; if empty, use an empty string. Do NOT recall it from memory. updated_at (output of date -u +%Y-%m-%dT%H:%M:%SZ), intent (one line).
    • sections: Done this stretch / In flight / Next concrete step / Open questions & risks. Capture only the live working thread — what you'd need to resume cleanly. Fold in $ARGUMENTS.
  4. Arm the reload, stamping this session as its owner: printf '%s' "$CLAUDE_CODE_SESSION_ID" > .reload/pending (if the variable is empty, touch .reload/pending instead — an un-owned arm is better than a wrong one).
  5. Tell the user in two lines: digest saved, reload armed — run /clear (or /compact) and the session rehydrates automatically; or /reload to pull it back manually.
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. 4d ago First seen · 38 lines · 22 tokens per session scan A 09a5e02d4666

Subscribe to this mod's changes

snapshot is a command published in the GitHub repository betmoar/cc-reload-plugin (1 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 552 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 2026-08-31.