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/dork-labs/dorkos/apigit clone --depth 1 https://github.com/dork-labs/dorkosWhat 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 | $0.00024 | $0.03164 |
| Opus 5 | $0.00012 | $0.01582 |
| Sonnet 5 | $0.00005 | $0.00633 |
| Haiku 4.5 | $0.00002 | $0.00316 |
Grade A, and why
api 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 2d 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API & Data Flow Debugging
Debug data-related issues by systematically tracing through the project's data flow layers. This command helps with API failures, data mismatches, stale cache, and service errors.
For anything on the messaging path — a room, a session turn, a task run, a chat integration — read
contributing/observability.mdand start fromdispatchId. Onedsp_<ULID>joins every hop of one message's life, sojq -c 'select(.dispatchId=="dsp_…")'gives you the whole chain in order rather than a layer at a time. If the server is still up,dorkos debug session <id>answers what is only in memory: the lifecycle, the write lock, and what the turn is parked on.
Project Data Flow Architecture
+-------------------+
| React Component | <- UI displays data (FSD layers)
+-------------------+
| TanStack Query | <- Client-side caching & fetching
+-------------------+
| Transport Layer | <- HttpTransport (REST/SSE) or DirectTransport (Obsidian)
+-------------------+
| Express Route | <- HTTP endpoints (Zod validation, boundary checks)
+-------------------+
| Service Layer | <- Business logic (agent-manager, binding-router, etc.)
+-------------------+
| Data Store | <- SQLite (dork.db) + JSONL transcripts + JSON state files
+-------------------+
Key Differences from Typical Projects
- SQLite, not PostgreSQL — Drizzle ORM (
packages/db) over SQLite (WAL mode), plus JSON state files - No server actions — All mutations go through Express REST endpoints
- Transport abstraction — Client uses
Transportinterface, not direct fetch - SDK transcripts — Sessions are derived from JSONL files on disk, not a database
- Feature-flag guarded — Relay/Mesh/Pulse endpoints return 503 when disabled
Arguments
Parse $ARGUMENTS:
- If
--url <url>flag provided, navigate to that URL - Remaining text describes the endpoint or feature with issues
- If empty, prompt for details
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.
- 2d ago First seen · 366 lines · 24 tokens per session scan A 3a5035dfe743
api is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 3,164 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
tidy
Consistency check for non-code repos with INDEX.md hierarchy. Verifies INDEX.md accuracy, MEMORY.md references, orphaned files, stale dates, and WAITING markers.
swarm-planner
Generates a structured execution plan with dependency tracking using the Swarms-inspired planning methodology.
review-queue
Display and manage the human review queue for parallel autonomous operations.
taskrunner-add
Add a task to the autonomous queue.
single-cli
ORCHESTRATOR. Run the autonomy loop as subagents in ONE terminal (coordination.mode=single-cli; default OFF; fail-closed). Re-runs decideCoordination, refuses if no independent verification remains, then drives a sequential builder/reviewer baton where the deterministic gate BINDS and the LLM critique is ADVISORY.