session-save

A session-saving command that records the current work, decisions, and context in a project file so a later session can resume it.

In plain words
What is it for?
Saving the state of ongoing development work for automatic loading in a future session.
Why use it?
It reduces the need to reconstruct what was happening after a session ends or is interrupted.

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/adilkalam/orca/session-save
Clone the repo
git clone --depth 1 https://github.com/adilkalam/orca
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,132 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 $0.00008 $0.01132
Opus 5 $0.00004 $0.00566
Sonnet 5 $0.00002 $0.00226
Haiku 4.5 $0.00001 $0.00113

Measured yesterday against content hash 7b1d07a9614e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-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 yesterday.

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/session-save.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/session-save - Save Session Context

PURPOSE: Capture current session state, tasks, and decisions for automatic loading on next session start.

EXPECTED OUTCOME: Create .orca/orchestration/active-task.md that SessionStart hook will auto-load.

NOTE: File is stored in .orca/orchestration/ (not temp/) to avoid accidental cleanup. The SessionStart hook automatically outputs this to STDOUT with 5 safeguards:

  • 48h freshness check (skips stale context)
  • 2000 char limit (truncates with indicator)
  • Graceful missing file (silent continue)
  • Absolute paths (reliable across directories)
  • Resume mode awareness (native --continue provides full transcript)

Step 1: Gather Session Information

Collect from user:

Use AskUserQuestion to gather context:

AskUserQuestion({
  questions: [
    {
      question: "What were you working on this session?",
      header: "Session Focus",
      multiSelect: false,
      options: [
        {
          label: "iOS app development",
          description: "Swift, SwiftUI, Xcode work"
        },
        {
          label: "Web app features",
          description: "Next.js, React, UI components"
        },
        {
          label: "Design system work",
          description: "Design commands, inspiration, briefs"
        },
        {
          label: "Infrastructure/tooling",
          description: "Build, deploy, CI/CD"
        }
      ]
    }
  ]
})

Then ask for details:

"Please summarize in 2-3 sentences:

  • What you accomplished this session
  • What you're planning to work on next
  • Any important decisions or blockers"

Step 2: Analyze Current State

Check git status:

git status --short
git log --oneline -5
git branch --show-current
basename $(git rev-parse --show-toplevel)

Detect project stack:

  • Check for package.json (Next.js, React, etc.)
  • Check for Podfile/Package.swift (iOS)
  • Check for app.json/expo (Expo)

Check for active tasks:

  • Modified files
  • Uncommitted changes
  • Recent commits

Read the full file on GitHub · 210 lines

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. yesterday First seen · 210 lines · 8 tokens per session scan A 7b1d07a9614e

Subscribe to this mod's changes

session-save is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 1,132 once invoked, about $0.0000 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.