save

A command that saves the current coding session's context for later recall. It records decisions, changed files, open questions, and other working details in local session storage and selected long-term memory.

In plain words
What is it for?
Use it at a checkpoint to save project state, unresolved questions, and durable lessons, then confirm where the checkpoint was stored.
Why use it?
It prevents important context from being lost when work is paused or continued in another session.

Command for Claude Code

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/cdeust/ai-architect-mcp-codebase/save
Clone the repo
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebase

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 231 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 $0.00000 $0.00231
Opus 5 $0.00000 $0.00115
Sonnet 5 $0.00000 $0.00046
Haiku 4.5 $0.00000 $0.00023

Measured 2d ago against content hash fd95f1a37c35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

save 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.

.claude/commands/session/save.md · 18 lines

What it actually says

Save Session Context

Save the current session's context for future recall.

Instructions

  1. Summarize the current session: decisions made, files changed, open questions, difficulty-book state.

  2. Session state is a block, not an archival fact (zetetic-team-subagents memory/contract.md §8b). Write the summary to the scoped working-state block via memory-tool.sh rethink /memories/<scope>/checkpoint.md (use create for the first checkpoint); the sync drainer replicates it to Cortex tagged memory-replica. Do NOT call cortex:remember for the session summary itself.

  3. If the session produced self-contained WHY-level facts (decision + rationale, rejected approach + root cause, lesson), store each via cortex:remember with tags: ["archival", "<project-name>", ...] AND agent_topic. Be selective.

  4. Also save locally: tools/session-store.sh save "<summary>"

  5. Confirm to the user what was saved (block path + number of archival entries, if any).

$ARGUMENTS

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 · 18 lines · 0 tokens per session scan A fd95f1a37c35

Subscribe to this mod's changes

save is a command published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 231 tokens. 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.