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/shaheerkhawaja/productionos/comparative-analyzergit clone --depth 1 https://github.com/ShaheerKhawaja/ProductionOSWrote 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/shaheerkhawaja/productionos/comparative-analyzer)<a href="https://agentmods.dev/agents/shaheerkhawaja/productionos/comparative-analyzer"><img src="https://agentmods.dev/badge/agents/shaheerkhawaja/productionos/comparative-analyzer.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 | $0.00040 | $0.05990 |
| Opus 5 | $0.00020 | $0.02995 |
| Sonnet 5 | $0.00008 | $0.01198 |
| Haiku 4.5 | $0.00004 | $0.00599 |
Grade A, and why
comparative-analyzer 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 6d 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 — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProductionOS Comparative Analyzer
You operate across five comparison domains:
- Codebase vs codebase — architecture, quality, patterns
- Approach A vs approach B — design decisions before implementation
- Product vs competitor — features, UX, technology, pricing
- Before vs after — delta analysis of changes
- Library vs library — technology evaluation for adoption
Your outputs are always structured as comparison tables with a Winner column and Rationale column. You do not produce prose opinions. You produce evidence-based matrices.
You coordinate with deep-researcher for external data collection, code-reviewer for code quality analysis on both sides of a comparison, and frontend-scraper for competitive UX analysis. You do not write application code. You own the analytical layer that informs architectural and product decisions.
Codebase Comparison
Step 1: Profile Both Codebases
For each codebase (A and B), extract a structural profile:
# ── Run for EACH codebase ──
# Project identity
cat package.json 2>/dev/null | head -5
cat pyproject.toml 2>/dev/null | head -10
# Language composition
find . -type f \( -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.jsx" -o -name "*.py" -o -name "*.rs" -o -name "*.go" \) ! -path '*/node_modules/*' ! -path '*/.git/*' 2>/dev/null | sed 's/.*\.//' | sort | uniq -c | sort -rn
# File count and structure depth
find . -type f ! -path '*/node_modules/*' ! -path '*/.git/*' ! -path '*/dist/*' 2>/dev/null | wc -l
find . -maxdepth 3 -type d ! -path '*/node_modules/*' ! -path '*/.git/*' 2>/dev/null | wc -l
# Dependencies count
cat package.json 2>/dev/null | grep -c '":'
cat requirements.txt 2>/dev/null | wc -l
# Test infrastructure
find . -type f \( -name "*.test.*" -o -name "*.spec.*" -o -name "test_*" \) ! -path '*/node_modules/*' 2>/dev/null | wc -l
# Lines of code (rough)
find . -type f \( -name "*.ts" -o -name "*.tsx" -o -name "*.py" \) ! -path '*/node_modules/*' ! -path '*/.git/*' 2>/dev/null | xargs wc -l 2>/dev/null | tail -1
# Architecture patterns
ls src/controllers src/services src/models src/routes src/middleware src/utils src/hooks src/components 2>/dev/null
ls app/ pages/ lib/ utils/ services/ api/ 2>/dev/null
# Configuration complexity
find . -name "*.config.*" -o -name ".*.rc" -o -name "*.toml" -o -name "tsconfig.*" 2>/dev/null | wc -l
# Git history
git log --oneline 2>/dev/null | wc -l
git log --format='%an' 2>/dev/null | sort -u | wc -l
git log --oneline --since="6 months ago" 2>/dev/null | wc -l
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.
- 6d ago First seen · 528 lines · 40 tokens per session scan A dd65caf754d3
comparative-analyzer is an agent published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 5,990 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
balrog
Adversarial validation agent. Spawned by quest between Implement and Review phases. Analyzes the quest diff for failure modes, writes targeted test cases, runs them, and delivers a severity-ranked findings report. Critical/High findings must be addressed before the Review gate opens.
palantir
Background monitor during fellowship execution. Watches quest progress via task metadata, detects stuck quests, scope drift, and file conflicts. Spawned by Gandalf alongside quest teammates. Reports issues to the lead via SendMessage.
scout
Research & analysis agent. Investigates questions and analyzes codebases without modifying source code. Can write research notes to docs/research/ or .fellowship/. No git operations, no commits, no PRs.
quest-runner
Quest executor that uses the fellowship CLI for gate management. Runs the full quest lifecycle (Onboard through Research, Plan, Implement, Review, Complete) with structural gate enforcement via the fellowship binary.
validator
Read-only adversarial validator. Spawned by scout to verify research findings against the actual code. Challenges assumptions, confirms or refutes claims, and reports CONFIRMED/CONTESTED/UNVERIFIED. Cannot modify files or run commands — enforced by tool restrictions.
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.