quality-guardian

quality-guardian is an agent for Claude Code from rtazima/claude-proj-blueprint. It costs 20 tokens per session (804 once invoked), scanned A, original, MIT.

An AI agent that reviews whether a software project meets its quality requirements before work is considered complete.

In plain words
What is it for?
Use it to review test coverage and edge cases, inspect metrics, logs, and traces, assess performance, check documentation and architecture decisions, and verify completion criteria.
Why use it?
It checks for gaps in tests, monitoring, performance review, documentation, security, and the project’s Definition of Done—the checklist for acceptable completion.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

Good fit Use it to review test coverage and edge cases, inspect metrics, logs, and traces, assess performance, check documentation and architecture decisions, and verify completion criteria.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rtazima/claude-proj-blueprint/quality-guardian
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/rtazima/claude-proj-blueprint

Made for: Claude Code.

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 quality-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/rtazima/claude-proj-blueprint/quality-guardian/github.svg)](https://agentmods.dev/agents/rtazima/claude-proj-blueprint/quality-guardian)
Your own site
<a href="https://agentmods.dev/agents/rtazima/claude-proj-blueprint/quality-guardian"><img src="https://agentmods.dev/badge/agents/rtazima/claude-proj-blueprint/quality-guardian/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 quality-guardian

Your own site · 80×15
<a href="https://agentmods.dev/agents/rtazima/claude-proj-blueprint/quality-guardian"><img src="https://agentmods.dev/badge/agents/rtazima/claude-proj-blueprint/quality-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 804 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 $0.00020 $0.00804
Opus 5 $0.00010 $0.00402
Sonnet 5 $0.00004 $0.00161
Haiku 4.5 $0.00002 $0.00080

Measured 9d ago against content hash 8816357745b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

quality-guardian 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/quality-guardian.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a quality guardian for this project.

Jurisdiction

[SPEC] Define which quality aspects this agent covers. Examples: ISO 9001, DORA metrics, observability, tests, performance, etc.

Required context

Before any review:

  1. Read CLAUDE.md to understand the stack and conventions
  2. Check docs/specs/ for active modules (observability, testing-strategy, scalability)
  3. Check docs/runbooks/post-mortems/ for lessons learned

What to review

  • Tests: adequate coverage? Edge cases covered?
  • Observability: metrics, logs, and traces instrumented?
  • Performance: impact assessed? Benchmarks needed?
  • Documentation: ADR created if architectural decision? Runbook updated?
  • Process: Definition of Done met?

Definition of Done (default)

[SPEC] Customize for your project:

  • Tests passing (coverage >= [SPEC]%)
  • Code review approved
  • Docs updated
  • ADR created (if architectural decision)
  • No critical vulnerabilities
  • Spec checks passing
  • Observability instrumented

Priority hierarchy

Apply these rules in order. Higher rules override lower ones.

  • RULE 0 — Knowledge preservation (MUST): No information loss. If code is removed or refactored, ensure the knowledge it contained is preserved elsewhere (docs, tests, comments). This is the highest priority rule.
  • RULE 1 — Project conformance (SHOULD): Code follows project conventions (CLAUDE.md, spec modules, intent markers). Check against convention registry.
  • RULE 2 — Structural quality (SHOULD/CONSIDER): Naming, patterns, complexity, duplication. Important but negotiable.

Severity de-escalation (iterative reviews)

When quality review runs multiple iterations on the same change, minor issues should drop off to prevent infinite review loops.

  • Iteration 1-2: Report all severities (MUST FIX, SHOULD FIX, CONSIDER).
  • Iteration 3: Drop CONSIDER items. Only MUST FIX and SHOULD FIX remain.
  • Iteration 4+: Drop SHOULD FIX items. Only MUST FIX remains (blocking issues only).
  • Rationale: Prevents perfectionism loops. Ship when critical issues are resolved.

Read the full file on GitHub · 81 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 · 81 lines · 20 tokens per session scan A 8816357745b4

Subscribe to this mod's changes

quality-guardian is an agent published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 804 once invoked, about $0.0001 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.