Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/atretyak1985/swarmerynpx agentmods add commands/atretyak1985/swarmery/dashboardWrote 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/atretyak1985/swarmery/dashboard)<a href="https://agentmods.dev/commands/atretyak1985/swarmery/dashboard"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/dashboard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/atretyak1985/swarmery/dashboard"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/dashboard.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00015 | $0.02784 |
| Opus 5 | $0.00008 | $0.01392 |
| Sonnet 5 | $0.00003 | $0.00557 |
| Haiku 4.5 | $0.00002 | $0.00278 |
Grade C, and why
dashboard scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
hook_count=$(find .claude/hooks -name "*.sh" | wc -l | tr -d ' ') Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
skill_count=$(find .claude/skills -mindepth 1 -maxdepth 1 -type d | wc -l | tr -d ' ') How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dashboard — Session & System Dashboard
Show a comprehensive dashboard of the current Claude Code session and the project's agent system status. Combine multiple data sources into a single structured report.
What to report
Collect ALL of the following data points in parallel, then present them in a single structured dashboard.
1. Current Session Stats
Read the session tracking file to get tool usage stats:
today=$(date +%Y%m%d)
SESSION_FILE=""
for f in /tmp/claude-session-*-${today}.jsonl /tmp/claude-session-${today}.jsonl; do
[ -f "$f" ] && [ -s "$f" ] && SESSION_FILE="$f"
done
if [ -n "$SESSION_FILE" ]; then
total=$(wc -l < "$SESSION_FILE" | tr -d ' ')
echo "Total tool calls: $total"
echo "--- By tool ---"
jq -r '.tool' "$SESSION_FILE" | sort | uniq -c | sort -rn
echo "--- Unique files ---"
jq -r 'select(.file != "") | .file' "$SESSION_FILE" | sort -u | wc -l | tr -d ' '
echo "--- Files list ---"
jq -r 'select(.file != "") | .file' "$SESSION_FILE" | sort -u | sed "s|${CLAUDE_PROJECT_DIR:-$(pwd)}/||"
echo "--- Timeline ---"
first_ts=$(head -1 "$SESSION_FILE" | jq -r '.ts')
last_ts=$(tail -1 "$SESSION_FILE" | jq -r '.ts')
echo "Start: $first_ts"
echo "Last: $last_ts"
else
echo "No session data for today"
fi
2. Active Tasks (agent-work.sh)
bash .claude/scripts/agent-work.sh list in_progress 2>/dev/null || echo "No active tasks"
3. Recent Completed Tasks
bash .claude/scripts/agent-work.sh list completed 2>/dev/null | tail -5 || echo "No completed tasks"
4. Agent System Health
# Count agents
agent_count=$(find .claude/agents -name "*.md" -not -name "README.md" | wc -l | tr -d ' ')
command_count=$(find .claude/commands -name "*.md" -not -name "README.md" | wc -l | tr -d ' ')
skill_count=$(find .claude/skills -mindepth 1 -maxdepth 1 -type d | wc -l | tr -d ' ')
hook_count=$(find .claude/hooks -name "*.sh" | wc -l | tr -d ' ')
echo "Agents: $agent_count | Commands: $command_count | Skills: $skill_count | Hooks: $hook_count"
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.
- 8d ago First seen · 261 lines · 15 tokens per session scan C c15539d5cf03
dashboard is a command published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 2,784 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
save-to-md
Save session documentation with Neo4j memory integration.
gws-docs
Read, create, and append content to Google Docs documents.
gws-chat
Send messages and manage Google Chat spaces.
send-email
Send an email via Google Workspace CLI.
gws-standup
Generate a standup report combining today's calendar and tasks.
meeting-prep
Prepare for your next meeting with agenda and attendees.