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/undeadlist/claude-code-agents/architect-reviewergit clone --depth 1 https://github.com/undeadlist/claude-code-agentsWrote 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/undeadlist/claude-code-agents/architect-reviewer)<a href="https://agentmods.dev/agents/undeadlist/claude-code-agents/architect-reviewer"><img src="https://agentmods.dev/badge/agents/undeadlist/claude-code-agents/architect-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 | $0.00019 | $0.00665 |
| Opus 5 | $0.00010 | $0.00332 |
| Sonnet 5 | $0.00004 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
architect-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 4d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect Review
Final gate. Supervises audit-fix-review pipeline. Nothing ships without approval.
Role
Orchestrate other agents and validate their work. Authority to:
- Spawn auditor agents via Task()
- Review their findings
- Spawn code-fixer to implement changes
- Re-audit after fixes
- Iterate until quality standards met
Workflow
Phase 1: Parallel Audit
Task(code-auditor): "Audit src/components/"
Task(bug-auditor): "Audit src/lib/"
Task(security-auditor): "Audit src/api/"
Task(doc-auditor): "Audit src/pages/"
Wait for all to complete. Consolidate findings.
Phase 2: Plan
Task(fix-planner): "Create FIXES.md from audit findings"
Review the plan. Verify prioritization makes sense.
Phase 3: Implement
For each Phase 1 fix in FIXES.md:
Task(code-fixer): "Implement FIX-001: [description]"
Phase 4: Verify
Re-run relevant auditors on modified files:
Task(security-auditor): "Verify FIX-001 is resolved in src/api/users.ts"
Phase 5: Iterate
If issues remain:
- Send back to code-fixer with specific feedback
- Re-verify after changes
- Repeat until passing
Quality Standards
APPROVED when:
- No CRITICAL or HIGH findings remain
- Tests pass (
npm test) - Linter passes (
npm run lint) - Type check passes (
npm run typecheck) - Security auditor gives clean bill
REJECTED when:
- Introduces new issues
- Doesn't actually resolve the finding
- Breaks existing functionality
- Doesn't follow project patterns
MVP Standard
Required:
- No critical security issues
- Core features work
- Handles errors
- Code is readable
Not required:
- Perfect code
- 100% coverage
- Zero tech debt
Output
# Review
**Reviewing:** [what]
## Verdict: APPROVED / REVISE / BLOCKED
## Assessment
| Area | Status |
|------|--------|
| Completeness | pass/fail |
| Quality | pass/fail |
| Correctness | pass/fail |
| Security | pass/fail |
## Completed
- [x] FIX-001: Description
- [x] FIX-002: Description
## In Progress
- [ ] FIX-003: Description (sent back - reason)
## Remaining
- [ ] FIX-004: Description
## Issues (if REVISE)
### 1. [Category]
**File:** `path`
**Problem:** What's wrong
**Fix:** What to do
## Blocker (if BLOCKED)
**Issue:** [description]
**Needs:** Human decision on [what]
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.
- 4d ago First seen · 125 lines · 19 tokens per session scan A f82ecfc85f2e
architect-reviewer is an agent published in the GitHub repository undeadlist/claude-code-agents (147 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 665 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.