session-resume

session-resume is a command for coding agents from adilkalam/orca. It costs 15 tokens per session (1,140 once invoked), scanned B, original, MIT.

A command for manually reloading saved session context, such as the current focus, tasks, decisions, and next steps, from a project file.

In plain words
What is it for?
Checking whether an active-task file exists, reading its contents, and verifying how recently it was updated.
Why use it?
It restores working context when automatic session loading failed or when the saved context needs to be refreshed during a session.

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-resume
Clone the repo
git clone --depth 1 https://github.com/adilkalam/orca
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,140 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00015 $0.01140
Opus 5 $0.00008 $0.00570
Sonnet 5 $0.00003 $0.00228
Haiku 4.5 $0.00002 $0.00114

Measured 3d ago against content hash da84eb11ed32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

session-resume scanned grade B with 1 finding 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat .claude/settings.local.json | grep -A 10 "SessionStart"
commands/session-resume.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/session-resume - Reload Session Context

PURPOSE: Manually load session context if SessionStart hook didn't fire or you need to refresh context mid-session.

WHEN TO USE:

  • SessionStart hook failed to load context
  • Want to reload context after significant changes
  • Debugging session continuity issues
  • Mid-session context refresh needed

Step 1: Check for Context File

if [ -f .orca/orchestration/active-task.md ]; then
  echo " Session context file found"
  cat .orca/orchestration/active-task.md
else
  echo " No session context file found"
  echo ""
  echo "To create one, run: /session-save"
  exit 1
fi

Step 2: Read and Display Context

Read the file:

Read(.orca/orchestration/active-task.md)

Parse and present:

Extract from the file:

  • Session focus area
  • Current tasks
  • Recent work/commits
  • Important decisions
  • Next steps

Step 3: Verify Context is Current

Check file age:

fileAge=$(( $(date +%s) - $(stat -f %m .orca/orchestration/active-task.md) ))
ageMinutes=$(( fileAge / 60 ))
ageHours=$(( fileAge / 3600 ))

if [ $ageHours -lt 1 ]; then
  echo "Context is fresh: ${ageMinutes} minutes old"
elif [ $ageHours -lt 24 ]; then
  echo "Context is recent: ${ageHours} hours old"
else
  ageDays=$(( ageHours / 24 ))
  echo " Context is ${ageDays} days old - may be stale"
  echo "Consider running /session-save to update"
fi

Step 4: Present Summary

 SESSION CONTEXT LOADED

Last Updated: [timestamp from file]
Age: [X minutes/hours/days ago]

FOCUS AREA:
[Session focus from file]

CURRENT TASKS:
[Tasks from file]

RECENT WORK:
[Recent commits/changes from file]

NEXT STEPS:
[Planned work from file]

DECISIONS & BLOCKERS:
[Important context from file]

---

Context loaded successfully! I'm now up to speed on your previous work.

Step 5: Ask for Updates

If context is stale (>24 hours):

 This context is [X days] old.

Has anything changed since then? For example:
- Completed any of the listed tasks?
- New priorities or blockers?
- Different direction?

If yes, consider running /session-save to update context.

Read the full file on GitHub · 221 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. 3d ago First seen · 221 lines · 15 tokens per session scan B da84eb11ed32

Subscribe to this mod's changes

session-resume is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,140 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.