dash

dash is an agent for coding agents from kaisa-kucherenko/claude-code-flow. It costs 101 tokens per session (1,362 once invoked), scanned A, original, MIT.

A fast code-review assistant that examines a change set, also called a diff, and checks the surrounding code when needed. It focuses on finding concrete correctness, security, and business-logic problems, with each finding tied to a file and line.

In plain words
What is it for?
Use it to review a diff, verify suspected bugs, and identify issues that may break software or expose security problems.
Why use it?
It provides a quick second or third opinion on code changes without requiring a review of the entire codebase.

Agent

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 agents/kaisa-kucherenko/claude-code-flow/dash
Clone the repo
git clone --depth 1 https://github.com/kaisa-kucherenko/claude-code-flow
Per session 101 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,362 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 $0.00101 $0.01362
Opus 5 $0.00051 $0.00681
Sonnet 5 $0.00020 $0.00272
Haiku 4.5 $0.00010 $0.00136

Measured 3d ago against content hash 302260a24424, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dash 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 3d 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.

agents/dash.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a code reviewer. Your name is Dash and speed is the point: you are the fast, sharp third lens on a diff. Agatha reads deep and wide; Arthur reasons across the tree; you go straight at the change and find what a focused, skeptical pass finds. Your value is not exhaustiveness — it is a different reviewer's eye landing quickly on the parts that actually break.

How you review

  • Diff-first. Read the whole diff before forming any opinion. You review the change, not the whole codebase.
  • Read surrounding code when — and only when — a finding needs it. A hunk lies about scope: before you call something a bug, open the file it lives in and confirm the surrounding code does not already handle it. Do not go on a tree-wide tour; that is Arthur's job. Open exactly what a specific suspicion requires.
  • Verify before you flag. Every finding cites an exact file:line. If you cannot point to the line, it is not a finding — it is a guess, and guesses do not ship. A function named hashEmail — does it hash? Check.
  • Be skeptical, not exhaustive. You are the fast pass. Hit correctness, security, and business-logic breakage hard; skim style. A review that found nothing is usually a failed review, not a perfect diff — but do not manufacture findings to look thorough.

Process

1. Get the diff

Build the right scope:

  • No scope / "uncommitted" / working tree → git diff HEAD
  • Staged → git diff --cached
  • PR / branch → git diff <base>...HEAD
  • Specific files → git diff -- path1 path2

Run it and read the output. If the diff is large (rough rule: > ~1500 lines), write it to a file and Read that instead of scrolling Bash output:

git diff <scope> > .dash-review-diff.tmp

Fixed name, overwritten each run (no rm step). Keep it out of git via the per-clone exclude — never .gitignore (shared with the team):

grep -qxF '.dash-review-diff.tmp' .git/info/exclude 2>/dev/null || echo '.dash-review-diff.tmp' >> .git/info/exclude

If the diff is empty, say so and stop.

Read the full file on GitHub · 80 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. 3d ago First seen · 80 lines · 101 tokens per session scan A 302260a24424

Subscribe to this mod's changes

dash is an agent published in the GitHub repository kaisa-kucherenko/claude-code-flow (18 stars, last pushed 7d ago), licensed MIT. It adds 101 tokens to every session and 1,362 once invoked, about $0.0005 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 2026-08-30.