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/allgit 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/all)<a href="https://agentmods.dev/commands/dork-labs/dorkos/all"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/all.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 | $0.00049 | $0.04177 |
| Opus 5 | $0.00024 | $0.02089 |
| Sonnet 5 | $0.00010 | $0.00835 |
| Haiku 4.5 | $0.00005 | $0.00418 |
Grade A, and why
all 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.
How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run every free, deterministic verification tier in this repo, in one pass, and produce a single report with a pass/fail verdict per tier. Then stop and ask before running anything that spends money or needs a live stack.
This is the run-everything entry point described in meta/chat-capabilities.md §11. It does not replace the individual commands — it sequences them and reports honestly on what actually ran.
The one rule that matters: a tier that did not execute is never green. See "Honest reporting" below — turbo's cache replay is designed to look exactly like a passing run.
Argument Parsing
Parse $ARGUMENTS:
skip:a,b— skip named tiers. Names:verify,unit,e2e,evals. Skipped tiers are reported asSKIPPED (requested), never as PASS.only:1,2— run only these tier numbers (1–4). Mutually exclusive withskip:.--yes-paid— the operator has pre-approved the gated tier, so Phase 6 runs its ladder without a second question. Without this flag, never start a paid tier on your own initiative.
Default (no arguments): tiers 1–4, then ask.
Results File
TIMESTAMP=$(date +%Y%m%d-%H%M%S)
RESULTS_DIR="test-results/test-all"
mkdir -p "$RESULTS_DIR"
RESULTS_FILE="$RESULTS_DIR/$TIMESTAMP.md"
Write the header immediately (Status: IN PROGRESS, the tier plan, git branch + git rev-parse --short HEAD) and append after every tier, so an interrupted run still leaves a truthful partial record. test-results/ is gitignored — the report is a local artifact, not a commit.
Full command output goes to $RESULTS_DIR/$TIMESTAMP-<tier>.log; the report links to it and quotes only the verdict lines. Never paste a thousand lines of turbo output into the report.
Phase 0 — Preflight
node -v && pnpm -v
git rev-parse --abbrev-ref HEAD && git status --short | head -20
ls node_modules >/dev/null 2>&1 || echo "WARNING: no node_modules — run 'pnpm install' first"
A dirty tree is fine (that is usually the point), but record it: a run against uncommitted work is only meaningful alongside the diff it tested.
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 · 222 lines · 49 tokens per session scan A dfa95f3c31a9
all is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 4,177 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
test-run
Run all tests and report coverage to @chief.
test-suite
Run comprehensive test suite with coverage analysis.
gsd:add-tests
Generate tests for a completed phase based on UAT criteria and implementation.
testing
Comprehensive testing through distributed execution.
verify
You are invoking the verify skill - comprehensive verification following Boris Cherny's pattern.
quality-check-command
This command performs comprehensive code quality checks. Use it before commits or when implementation is complete.