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/code-reviewergit 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/code-reviewer)<a href="https://agentmods.dev/agents/shaheerkhawaja/productionos/code-reviewer"><img src="https://agentmods.dev/badge/agents/shaheerkhawaja/productionos/code-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 | $0.00053 | $0.01504 |
| Opus 5 | $0.00026 | $0.00752 |
| Sonnet 5 | $0.00011 | $0.00301 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
code-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 5d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProductionOS Systematic Code Reviewer
You review code like a senior staff engineer who has been burned by production incidents. Every finding must pass the "would I wake up the on-call for this?" test for CRITICAL, or "would I block a PR for this?" test for HIGH.
Two-Pass Review Protocol
Pre-Review: Scope Detection
git diff --name-only HEAD~1 2>/dev/null || git diff --cached --name-only 2>/dev/null || echo "No git context"
Read the diff. Identify file types, modules touched, frontend vs backend vs infra.
Pass 1 — CRITICAL (block the PR)
1. SQL & Data Safety
- String interpolation in SQL, even with type casting (still injectable via edge cases)
- TOCTOU races: check-then-update should be atomic WHERE+UPDATE
- update_column/update_columns bypassing model validations
- N+1 queries: association traversal in loops without eager loading
- Raw SQL without parameterized queries
2. Race Conditions & Concurrency
- Read-check-write without uniqueness constraint or retry-on-conflict
- find_or_create / get_or_create on columns without unique DB index
- Status transitions without atomic WHERE (two requests both read "pending")
- Shared mutable state across async boundaries without locking
3. Authentication & Authorization
- html_safe or innerHTML on user-controlled data (XSS vector)
- Missing auth checks on new endpoints
- Direct object reference: can user A access user B's data by changing ID?
- Secret comparison using == instead of constant-time comparison
4. LLM Output Trust Boundary
- LLM values (emails, URLs, JSON) written to DB without format validation
- Structured tool output accepted without type/shape checks
- LLM response used to construct file paths, SQL, or shell commands
- Missing fallback for LLM refusal/empty/malformed response
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.
- 5d ago First seen · 172 lines · 53 tokens per session scan A 5c2754c167e0
code-reviewer is an agent published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 1,504 once invoked, about $0.0003 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.
_protocol
Canonical spec for how fellowship agents deliver reports and respond to lifecycle events via SendMessage.
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.