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.
npx agentmods add commands/adilkalam/orca/session-resumegit clone --depth 1 https://github.com/adilkalam/orcaWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00015 | $0.01140 |
| Opus 5 | $0.00008 | $0.00570 |
| Sonnet 5 | $0.00003 | $0.00228 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade B, and why
session-resume scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/settings.local.json | grep -A 10 "SessionStart" How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/session-resume - Reload Session Context
PURPOSE: Manually load session context if SessionStart hook didn't fire or you need to refresh context mid-session.
WHEN TO USE:
- SessionStart hook failed to load context
- Want to reload context after significant changes
- Debugging session continuity issues
- Mid-session context refresh needed
Step 1: Check for Context File
if [ -f .orca/orchestration/active-task.md ]; then
echo " Session context file found"
cat .orca/orchestration/active-task.md
else
echo " No session context file found"
echo ""
echo "To create one, run: /session-save"
exit 1
fi
Step 2: Read and Display Context
Read the file:
Read(.orca/orchestration/active-task.md)
Parse and present:
Extract from the file:
- Session focus area
- Current tasks
- Recent work/commits
- Important decisions
- Next steps
Step 3: Verify Context is Current
Check file age:
fileAge=$(( $(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.
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.
- 3d ago First seen · 221 lines · 15 tokens per session scan B da84eb11ed32
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.