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/execute)<a href="https://agentmods.dev/commands/dork-labs/dorkos/execute"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/execute/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/execute"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/execute.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 | $0.00017 | $0.00544 |
| Opus 5 | $0.00009 | $0.00272 |
| Sonnet 5 | $0.00003 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
execute 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 yesterday.
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
Execute UI audit batches
Batches: $ARGUMENTS
Read .claude/skills/auditing-ui/SKILL.md (the ownership contract is §5, landing is §7) and
audits/runs/ui/profile.md. This command adds only the fence checks; the skill owns everything
else.
Contract
-
Verify the fence before touching anything. For every batch item in range: its
blockedByedge to the run'stype/metapromotion-decision item is still open, and the item carries noagent/*label. Read the labels as leaf names (skill §5). If either check fails, the item was already promoted to the workflow path and is no longer yours: stop and report it. -
Confirm the fork is the audit path. Working here means the fence stays up against the workflow engine for the whole batch. If the operator meant the workflow path, the move is removing the edge and letting the normal lifecycle take over, not running this command.
-
Claim in the plugin namespace only —
ui-audit/in-progress(notaudit/claimed: Linear's team-wide label-name uniqueness collides with the existingagent/claimed), neveragent/*, and never with a label write computed from a stale read (skill §5). -
Land the work by skill §7's playbook, adapted to the profile: one worktree per batch, batches grouped so parallel branches touch disjoint files, an adversarial review on the branch before the PR opens (
assets/review-brief.md), then finalize. Walk each batch's findings item by item; simplify-first is reviewable. -
Items stay blocked until they close. Never resolve the
blockedByedge to unblock yourself. The item goes to done when its PR merges, still fenced, and the edge dies with it. -
Close out the run. When every batch in the run is promoted or closed, close the
type/metapromotion-decision item. It has an end of life on purpose: left open, it becomes the stale ledger a backlog groom sweeps at.
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.
- yesterday First seen · 42 lines · 17 tokens per session scan A 5197e7490d2f
execute is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 544 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 2026-09-08.
Other commands, from other repositories
scout-work
Interactive work session — walks through today's actionable items one at a time, presents a recommended action with draft content, and executes each one only with explicit approval. Runs in the current conversation (not as a background session).
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
modernize-preflight
Environment readiness check — analysis tools, build toolchain, source completeness, telemetry access.
OPSX: Bulk Archive
Archive multiple completed changes at once.
modernize-status
Where am I in the modernization workflow — artifact inventory, staleness, secrets hygiene, next step.
sp.taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.