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/arpitnath/claude-capsule-kit/load-sessiongit clone --depth 1 https://github.com/arpitnath/claude-capsule-kitWrote 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.
[](https://agentmods.dev/commands/arpitnath/claude-capsule-kit/load-session)<a href="https://agentmods.dev/commands/arpitnath/claude-capsule-kit/load-session"><img src="https://agentmods.dev/badge/commands/arpitnath/claude-capsule-kit/load-session.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00007 | $0.00425 |
| Opus 5 | $0.00003 | $0.00212 |
| Sonnet 5 | $0.00001 | $0.00085 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
load-session 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.
What it actually says
Load Session
Load a previously synced session summary from GitHub for context.
Usage
Provide the session path from /sessions output:
/load-session my-project/2024-12-13-abc12345
Load Session
# Get session path from argument (passed after command)
SESSION_PATH="$1"
if [ -z "$SESSION_PATH" ]; then
echo "Usage: /load-session <project>/<session>"
echo ""
echo "Example: /load-session my-project/2024-12-13-abc12345"
echo ""
echo "Run /sessions to see available sessions"
exit 0
fi
# Load sync config
if [ ! -f ".claude/sync-config.json" ]; then
echo "Session sync not configured. Run /sync-enable first."
exit 0
fi
SYNC_REPO=$(python3 -c "import json; print(json.load(open('.claude/sync-config.json')).get('repo', ''))" 2>/dev/null)
if [ -z "$SYNC_REPO" ]; then
echo "No sync repo configured"
exit 0
fi
# Fetch and display summary
echo ""
echo "📄 Loading session: $SESSION_PATH"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo ""
SUMMARY=$(gh api "repos/$SYNC_REPO/contents/sessions/$SESSION_PATH/summary.md" -q '.content' 2>/dev/null | base64 -d)
if [ -z "$SUMMARY" ]; then
echo "❌ Session not found: $SESSION_PATH"
echo ""
echo "Run /sessions to see available sessions"
exit 1
fi
echo "$SUMMARY"
Notes
- The summary provides context for continuing the session
- Copy the "Continue Prompt" section to start where you left off
- Works across devices via GitHub MCP in Claude Web/Desktop
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.
- 4d ago First seen · 69 lines · 7 tokens per session scan A 6735c98e9989
load-session is a command published in the GitHub repository arpitnath/claude-capsule-kit (90 stars, last pushed 3mo ago), licensed MIT. It adds 7 tokens to every session and 425 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 2026-08-30.
Other commands, from other repositories
research
Research external topics, create comprehensive analysis, and incorporate learnings into memory systems.
memory-explore
DEPRECATED: Use the exploring-knowledge-graph skill instead. Deep exploration of Forgetful knowledge graph with entity traversal.
memory-list
DEPRECATED: Use Serena listmemories instead. Lists recent memories from Forgetful with optional project filtering.
memory-search
Search memories semantically using Forgetful with query context for improved ranking. Use when retrieving specific knowledge or verifying memory existence.
memory-save
DEPRECATED: Use Serena writememory instead. Save current context as atomic memory in Forgetful.
memory-gc
Inspect or rotate hunt-memory JSONL files (audit.jsonl, patterns.jsonl, journal.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.