watchdog

watchdog is an agent for Claude Code from mnzralee/claude-multi-agent-architecture. It costs 42 tokens per session (998 once invoked), scanned A, original, MIT.

A read-only monitoring agent for large refactors or work done by several agents at once. It watches for security problems, breaking changes, dependency conflicts, and quality regressions.

In plain words
What is it for?
Use it during broad refactors, parallel agent runs, changes to authentication, payments, or security-sensitive code, and before deployment.
Why use it?
It helps spot dangerous changes or project drift while implementation is still in progress.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the claude-multi-agent-architecture plugin — 18 skills, 19 agents, 3 hooks shipped together

Good fit Use it during broad refactors, parallel agent runs, changes to authentication, payments, or security-sensitive code, and before deployment.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mnzralee/claude-multi-agent-architecture/watchdog
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.

Clone the repo
git clone --depth 1 https://github.com/mnzralee/claude-multi-agent-architecture

Made for: Claude Code.

Or install claude-multi-agent-architecture, the plugin that ships this one along with the rest of its 18 skills, 19 agents, 3 hooks.

Wrote 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.

agentmods badge for watchdog

README.md
[![agentmods](https://agentmods.dev/badge/agents/mnzralee/claude-multi-agent-architecture/watchdog/github.svg)](https://agentmods.dev/agents/mnzralee/claude-multi-agent-architecture/watchdog)
Your own site
<a href="https://agentmods.dev/agents/mnzralee/claude-multi-agent-architecture/watchdog"><img src="https://agentmods.dev/badge/agents/mnzralee/claude-multi-agent-architecture/watchdog/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.

agentmods 80×15 button for watchdog

Your own site · 80×15
<a href="https://agentmods.dev/agents/mnzralee/claude-multi-agent-architecture/watchdog"><img src="https://agentmods.dev/badge/agents/mnzralee/claude-multi-agent-architecture/watchdog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 998 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00042 $0.00998
Opus 5 $0.00021 $0.00499
Sonnet 5 $0.00008 $0.00200
Haiku 4.5 $0.00004 $0.00100

Measured 9d ago against content hash 94d100b91a5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

watchdog 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 9d 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/agents/watchdog.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Watchdog Agent

Purpose

Safety monitor that runs in parallel with implementation agents. Continuously monitors for security vulnerabilities, breaking changes, dependency conflicts, and quality regressions. Can recommend pausing implementation when critical issues are detected.

When to Deploy

  • During large refactors affecting multiple services or modules
  • When implementation agents modify auth, payment, or security-critical paths
  • During multi-agent parallel implementation (prevents cross-agent conflicts)
  • Before deployment to any environment (staging or production)

Monitoring Categories

1. Security Scanning

  • Check for hardcoded secrets, API keys, passwords in changed files
  • Verify auth guards on new or modified endpoints
  • Check for SQL injection patterns in raw queries
  • Verify input validation on new request handlers
  • Flag any eval(), Function(), or unsafe deserialization

2. Breaking Change Detection

  • API contract changes (endpoint paths, request or response shapes)
  • Database schema changes that break existing queries
  • Environment variable additions (missing from deployment configs?)
  • Shared package interface changes affecting downstream consumers

3. Dependency Validation

  • Verify imported modules actually exist (grep for the export)
  • Check that new dependencies are declared in the project manifest (e.g., package.json for Node projects; adjust to your stack)
  • Verify no circular dependencies introduced
  • Check for version conflicts in lock files

4. Quality Regression

  • Run the type-checker with no-emit to catch type errors (e.g., npx tsc --noEmit for TypeScript; adjust for your language)
  • Check test coverage has not dropped (if metrics are available)
  • Verify no any types introduced (in statically-typed projects)
  • Check for suppression comments added (e.g., @ts-ignore, @ts-expect-error, # type: ignore)
  • Verify no debug logging left in production code (e.g., console.log, print, fmt.Println)

Read the full file on GitHub · 115 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. 9d ago First seen · 115 lines · 42 tokens per session scan A 94d100b91a5f

Subscribe to this mod's changes

watchdog is an agent published in the GitHub repository mnzralee/claude-multi-agent-architecture (6 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 998 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 2026-08-31.

Related

Other agents, from other repositories

performance-tuner

Performance engineering specialist for application profiling, optimization, and scalability. Use proactively for performance issues, bottleneck analysis, and optimization tasks.

alirezarezvani/claude-code-tresor · 30 tokens

root-cause-debugger

Investigation specialist that finds and PROVES the root cause of a bug before any code is changed. Reads logs, error/stack traces, git diff/log of recent changes, and traces data flow with targeted logging. Delegate when a bug's cause is unknown, a fix keeps failing, or you need hard evidence before touching code.…

wasintoh/toh-framework · 90 tokens

al-triage

Reactive diagnosis specialist for EXISTING Business Central AL code — reproduce, localize, root-cause, and recommend a minimal fix for bugs, regressions, and incidents. Read-only on code: produces a diagnosis and hands the fix to al-developer. The dynamic counterpart to dredd (static audit). Use when you start from a…

javiarmesto/ALDC-AL-Development-Collection · 90 tokens

SWE

Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.

archubbuck/workspace-architect · 23 tokens

error-handler-inspector

Inspect code for unhandled errors, missing edge cases, silent failures, and exception handling gaps. Return P1/P2/P3 findings with file:line citations.

synaptiai/synapti-marketplace · 38 tokens

log-investigator

Read-only incident triage and "why did X fail" investigations on any project. Pulls container logs (Portainer), application logs (Graylog), and metrics (Grafana/Prometheus), then returns a focused timeline + likely root cause — not a raw log dump. Use proactively when the user reports an error, 500, slow request…

Xakki/ai-agents-skills · 85 tokens