ask

A repository question-answering command that checks the project’s own guides, architecture notes, rules, and related documentation before answering.

In plain words
What is it for?
Use it to ask how to implement a task in the repository, including questions about its tools, conventions, and design decisions.
Why use it?
It reduces guesswork when you need to understand how a particular codebase expects a task to be done.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/dork-labs/dorkos/ask
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 496 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00008 $0.00496
Opus 5 $0.00004 $0.00248
Sonnet 5 $0.00002 $0.00099
Haiku 4.5 $0.00001 $0.00050

Measured 2d ago against content hash d5f25e7d988f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ask 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.

.claude/commands/system/ask.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Help

Answer the question in $ARGUMENTS: how to accomplish a task in this repository, using Claude Code or manually.

Search order

Consult these sources, in order, until you can answer confidently:

  1. .claude/README.md — complete harness inventory: every command, agent, skill, rule, and hook, plus naming conventions and maintenance guides
  2. AGENTS.md — project architecture, conventions, quality standards
  3. decisions/ — ADRs explaining why things are the way they are (use decisions/manifest.json to find by topic)
  4. contributing/ — 28 developer guides with detailed patterns (contributing/INDEX.md maps topics to guides)
  5. .claude/rules/ — path-specific rules (each has paths: frontmatter declaring which files it governs)

Read the files the question actually touches — don't answer from memory when a source file can confirm.

Escalation

  • Claude Code / Agent SDK / Claude API questions not answered by local docs: dispatch the claude-code-guide agent — it has direct access to official documentation and is authoritative for hooks, skills, slash commands, MCP, settings, and SDK usage.
  • Non-Claude topics (libraries, general patterns): WebSearch.

When no process exists

If the repo has no defined process for the question, say so plainly, give best-effort guidance from similar patterns, then suggest the right follow-up:

  • /system:learn — when experimentation is needed to figure out the approach first
  • /system:update — when the fix/process is already known and just needs codifying

Answer format

Give a direct answer with concrete file paths. When both exist, show both the Claude Code method (slash command, agent, or skill — prefer a slash command when one exists) and the manual method (the actual files/commands to touch). Note relevant caveats, e.g. /flow:* commands require the flow plugin (dork-labs/marketplace) loaded via --plugin-dir. Offer to execute the Claude Code method when that's clearly what the user wants.

Read the full file on GitHub · 38 lines

Changes

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.

  1. 2d ago First seen · 38 lines · 8 tokens per session scan A d5f25e7d988f

Subscribe to this mod's changes

ask is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed 2d ago), licensed MIT. It adds 8 tokens to every session and 496 once invoked, about $0.0000 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.