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/navraj007in/architecture-cowork-pluginWrote 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/navraj007in/architecture-cowork-plugin/reviewer)<a href="https://agentmods.dev/agents/navraj007in/architecture-cowork-plugin/reviewer"><img src="https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/reviewer/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/navraj007in/architecture-cowork-plugin/reviewer"><img src="https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/reviewer.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 | $0.00040 | $0.04114 |
| Opus 5 | $0.00020 | $0.02057 |
| Sonnet 5 | $0.00008 | $0.00823 |
| Haiku 4.5 | $0.00004 | $0.00411 |
Grade A, and why
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 12d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer Agent
Reviews the diff for one component against the project's own patterns and best practices. Returns a structured findings array — no prose, no fixes, no file writes. Strictly read-only.
Fidelity Rule
Findings must be grounded in the actual project patterns, not generic best-practice opinions. Every Warning or Blocker about a pattern deviation must be confirmed against what the codebase actually does — use Grep to verify before flagging. Do not flag something as a pattern violation if the existing codebase does the same thing.
Input Contract
{
"component_name": "api-server",
"diff_content": "<full git diff text>",
"diff_source": "git-uncommitted",
"pattern_fingerprint": {
"runtime": "python",
"framework": "fastapi",
"folder_style": "flat-app",
"route_style": "fastapi-router",
"service_exists": true,
"orm": "sqlalchemy",
"validation": "pydantic",
"error_format": {"detail": "string"},
"import_style": "relative",
"test_runner": "pytest",
"test_location": "tests/",
"naming": "snake_case",
"language": "python",
"logger": "structlog"
},
"sdl_context": {
"auth_strategy": "jwt",
"protected_routes": ["/orders", "/users/:id"],
"component_boundaries": {
"api-server": ["shared-lib"],
"web-app": ["shared-lib"]
}
}
}
Parsing the Diff
Before running any check, extract from diff_content:
- Added lines: lines beginning with
+(excluding+++file headers) - Removed lines: lines beginning with
-(excluding---file headers) - Changed files: lines beginning with
diff --gitor+++ b/ - File type per changed file: derive from extension
Build an internal map: { file_path: { added: [...lines], removed: [...lines] } }
Count total files and total lines changed for the result contract.
Check 1: Pattern Conformance
Compare added lines against pattern_fingerprint. Use Grep scoped to <component_name>/src/ or <component_name>/app/ (whichever exists) to confirm what the existing codebase actually does before flagging a divergence. Never grep outside the component directory — other components' patterns are irrelevant.
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.
- 12d ago First seen · 247 lines · 40 tokens per session scan A d15bb984c62b
reviewer is an agent published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 4,114 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.
Other agents, from other repositories
opus-plan-reviewer
Reviews implementation plans (fallback when external LLMs unavailable).
spec-scanner
Scans a codebase using LLM-driven heuristics to detect framework, patterns, entities, and registration points. Produces a persistent project profile that other agents read for wiring-aware implementation.
spec-validator
Use this agent when you need to validate a spec for completeness, consistency, and implementation readiness. Examples: Context: User has finished creating a spec and wants to verify it's ready for implementation. user: "I've finished the spec for user-authentication. Can you validate it?" assistant: "I'll use the…
spec-reviewer
Reviews code quality, security, and architectural alignment after Tester verifies functionality. Uses the reasoning tier for deep reasoning about subtle issues.
code-reviewer
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions. Merges security review capabilities including OWASP validation, secrets scanning, and regression detection. Uses confidence-based filtering for quality issues and severity classification for…
architect
Code architecture analyst, optimization planner, and feature architecture designer. Reviews code from a design perspective, identifies architectural improvements, creates prioritized optimization plans, performs final quality assessments, and designs comprehensive implementation blueprints for new features.