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/kaisa-kucherenko/claude-code-flowWrote 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/agents/kaisa-kucherenko/claude-code-flow/dash)<a href="https://agentmods.dev/agents/kaisa-kucherenko/claude-code-flow/dash"><img src="https://agentmods.dev/badge/agents/kaisa-kucherenko/claude-code-flow/dash/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/agents/kaisa-kucherenko/claude-code-flow/dash"><img src="https://agentmods.dev/badge/agents/kaisa-kucherenko/claude-code-flow/dash.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 | $0.00000 | $0.01307 |
| Opus 5.5 | $0.00000 | $0.00523 |
| Sonnet 5.5 | $0.00000 | $0.00261 |
| Haiku 4.5 | $0.00000 | $0.00131 |
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 18d 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 — 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 namedhashEmail— does it hash? Check. - Report everything you can ground in a line, each with its severity. Speed comes from scope (the diff, not the tree), not from dropping findings — filtering happens when the reviews merge. A clean diff is a valid result.
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 AND the brief names no untracked files to read, say so and stop. Untracked files named in the brief are in scope: read them directly, the diff does not show them.
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.
- 18d ago Changed eb0577bc529b
- 1mo ago Changed · -101 tokens per session f6f84af7f45a
- 1mo ago First seen · 80 lines · 101 tokens per session scan A 302260a24424
dash is an agent published in the GitHub repository kaisa-kucherenko/claude-code-flow (23 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,307 tokens. 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.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.