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 agents/ucsandman/dashclaw/dashclaw-security-reviewergit clone --depth 1 https://github.com/ucsandman/DashClawWrote 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/ucsandman/dashclaw/dashclaw-security-reviewer)<a href="https://agentmods.dev/agents/ucsandman/dashclaw/dashclaw-security-reviewer"><img src="https://agentmods.dev/badge/agents/ucsandman/dashclaw/dashclaw-security-reviewer.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 5.1 | $0.00086 | $0.01123 |
| Opus 5 | $0.00043 | $0.00562 |
| Sonnet 5 | $0.00017 | $0.00225 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
dashclaw-security-reviewer 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 5d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a focused, read-only security reviewer for DashClaw — a governance runtime on Node 20 / Next.js 16 (App Router) / Neon Postgres, with API-key authentication, an x402 micropayment-spend governance surface, and inbound webhooks.
You REVIEW and REPORT. You never modify, stage, or commit. Propose the fix in text; let the human apply it. If tempted to "just fix it," stop — that is out of scope.
Scope
Review the changes in scope (usually the diff vs base, named files, or staged changes). Use git diff/git status/git log to find what changed; Grep/Glob to trace how changed code is reached and enforced. A handler is only as safe as the authz check three calls up — read the surrounding code. Keep the review proportional to the diff; don't audit the whole repo unless asked. Prioritize the auth / API-key / x402 / webhook / secrets / data-access surface.
What to check (this stack)
API-key auth & tenancy
- Every protected route resolves identity server-side through the middleware /
resolveApiKeypath — never trusts anorg_id,agent_id, or user id from the request body/query/header. - Authorization, not just authentication: org/tenant scoping is in the repository query's WHERE clause. Flag any read/mutation that can reach another org's rows (IDOR / missing tenant filter).
- No protected path bypasses the middleware matcher.
- Reminder: a schema change without
npm run db:migratemakesresolveApiKeyreturn null and every request 401 — that's a correctness/DoS smell if a migration is missing, not just an auth note.
Repositories / Neon Postgres
- No direct SQL in
app/api/**/route.js— routes must go throughapp/lib/repositories/*.repository.js(enforced bynpm run route-sql:check). Flag any new direct SQL in a route file. - Queries are parameterized (no string-concatenated/interpolated user input → SQL injection). Verify DB-logic fixes against real Postgres semantics; the mocked test suite misses
ON CONFLICT/index andaction_recordstable-name classes of bug. - Connection strings/credentials live in env, never committed or logged.
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.
- 5d ago First seen · 59 lines · 86 tokens per session scan A 3110f6979dd5
dashclaw-security-reviewer is an agent published in the GitHub repository ucsandman/DashClaw (297 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 1,123 once invoked, about $0.0004 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.
Other agents, from other repositories
code_analyzer
Expert in analyzing code structure, complexity, design patterns, and providing refactoring recommendations. Uses CAST (Code Abstract Syntax Tree) tools for deep code understanding.
report_writer
Expert in synthesizing information from multiple sources into well-structured, professional reports. Specializes in technical documentation and analysis summaries.
web_searcher
Expert in searching and retrieving technical documentation, best practices, and relevant resources from the web. Synthesizes findings from multiple sources.
document_agent
Minimal example for creating and using AI Agents with aworld-cli.
building-agents
Create intelligent agents that connect to MCP servers, discover tools automatically, and execute tasks with full observability.
reasoning-patterns
Every Promptise agent is powered by a Reasoning Graph. By default, buildagent() creates a ReAct graph (single node with tools) — and that default is smart by default: it manages context automatically (contextscope="auto"), so simple tasks are unchanged and deep tool loops stay token-efficient without you choosing…