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.
git clone --depth 1 https://github.com/dork-labs/dorkosWrote 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/dork-labs/dorkos/data)<a href="https://agentmods.dev/commands/dork-labs/dorkos/data"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/data/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/dork-labs/dorkos/data"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/data.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 | $0.00009 | $0.02718 |
| Opus 5.5 | $0.00004 | $0.01087 |
| Sonnet 5.5 | $0.00002 | $0.00544 |
| Haiku 4.5 | $0.00001 | $0.00272 |
Grade A, and why
data 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Debugging
Inspect and verify database state and subsystem data files directly. Use this command to:
- View SQLite database tables and data
- Inspect relay state files (adapters, bindings, sessions, mailboxes)
- Debug "data not showing" issues
- Verify pulse schedule and run state
- Check mesh agent registry
Data Architecture
DorkOS stores data in the .dork directory:
{DORK_HOME}/
├── config.json # Server configuration
├── dork.db # SQLite database (WAL mode)
├── logs/
│ └── dorkos.log # NDJSON structured logs
└── relay/
├── adapters.json # Adapter configurations
├── bindings.json # Adapter-agent bindings
├── sessions.json # Active session mappings
├── access-rules.json # Access control rules
└── mailboxes/ # Per-subject message files
└── relay.*.json # Message queues by subject
DORK_HOME Location
| Environment | Location |
|---|---|
| Development | apps/server/.temp/.dork/ |
| Production | ~/.dork/ (or DORK_HOME env var) |
Arguments
Parse $ARGUMENTS:
- If a table name is provided, query that SQLite table
- If a SQL query is provided, execute it
- If
--relayflag, inspect relay state files - If
--pulseflag, inspect pulse schedules and runs - If
--meshflag, inspect mesh agent registry - If empty, show overview and prompt for action
Phase 1: Data Overview
1.1 Show Available Data Sources
DORK_HOME="apps/server/.temp/.dork"
echo "=== Config ==="
cat "$DORK_HOME/config.json" | python3 -m json.tool
echo "=== SQLite Tables ==="
sqlite3 "$DORK_HOME/dork.db" ".tables"
echo "=== Relay State Files ==="
ls -la "$DORK_HOME/relay/" 2>/dev/null
echo "=== Log Files ==="
ls -la "$DORK_HOME/logs/" 2>/dev/null
1.2 Determine Action
AskUserQuestion:
question: "What would you like to inspect?"
header: "Action"
options:
- label: "SQLite database"
description: "Query pulse, relay, or mesh tables in dork.db"
- label: "Relay state files"
description: "Inspect adapters, bindings, sessions, mailboxes"
- label: "Server configuration"
description: "View config.json settings"
- label: "Run a custom query"
description: "Execute a specific SQL query"
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.
- 2mo ago First seen · 352 lines · 9 tokens per session scan A a3b2465d6507
data is a command published in the GitHub repository dork-labs/dorkos (12 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 2,718 once invoked, about $0.0000 per session on Opus 5.5. 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.
Other commands, from other repositories
debug-issue
I'm experiencing the following issue: {{1}}.
verify-architecture
Run 64 HOR rules and structural verification on the current codebase.
build-fix
Incrementally fix TypeScript and build errors with minimal diffs. Fix one error at a time for safety.
refactor-clean
Refactor provided code for cleanliness, maintainability, and alignment with SOLID principles and modern best practices — no over-engineering.
svelte:storybook-troubleshoot
Diagnose and fix common Storybook issues in SvelteKit projects, including build errors, module problems, and configuration issues.
checklist
Generate a custom checklist for the current feature based on user requirements.