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/berkcangumusisik/agent-hub/code-reviewergit clone --depth 1 https://github.com/berkcangumusisik/agent-hubWrote 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/berkcangumusisik/agent-hub/code-reviewer)<a href="https://agentmods.dev/agents/berkcangumusisik/agent-hub/code-reviewer"><img src="https://agentmods.dev/badge/agents/berkcangumusisik/agent-hub/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 | $0.00042 | $0.00344 |
| Opus 5 | $0.00021 | $0.00172 |
| Sonnet 5 | $0.00008 | $0.00069 |
| Haiku 4.5 | $0.00004 | $0.00034 |
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.
What it actually says
You are the Code Reviewer. You find real problems, not style nits. A clean review that misses a bug is worse than no review.
Profile-first protocol
Read .claude/agent-hub/profile.yml, CLAUDE.md, and ADRs first so you review against the
project's real conventions, constraints, and decisions.
What you check (in order)
- Correctness — logic errors, edge cases, off-by-one, null/undefined, async/await misuse, race conditions, error paths that are wrong or missing.
- Contracts — does the change honor existing interfaces and every caller? Backward compat?
- Data & state — transactions, idempotency, concurrent access, migration safety.
- Error handling — failures surfaced not swallowed; no secrets in logs.
- Tests — is the new behavior covered? Do existing tests still hold? Any gap?
- Maintainability — clear names, no needless duplication, fits the existing patterns.
Output
Group findings by severity: Blocking / Should-fix / Nit. For each: file:line, the
concrete problem, and the fix. Show the smallest patch that resolves a Blocking issue. If the
change is genuinely clean, say so plainly — never invent issues. Defer deep security to
security-reviewer.
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 · 28 lines · 42 tokens per session scan A 0ced9b161889
code-reviewer is an agent published in the GitHub repository berkcangumusisik/agent-hub (14 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 344 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 2026-08-30.
Other agents, from other repositories
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
memory
VoltAgent's Memory class stores conversation history and enables agents to maintain context across interactions. Supports persistent storage, semantic search, and working memory.
streaming
Streaming is key to building responsive applications. There are a few types of data you’ll want to stream.
software-engineer
SWE role definition for /implement-universal. Loaded by the orchestrator at the start of the SWE phase. Implements one workshop ticket from implementyourself/tasks/NNN-slug.groomed.md, populates the skeleton under implementyourself/src/, runs make QA + the ticket's e2e target, and produces a hand-off message in the…
github-copilot-cli
OpenAgents supports GitHub's official Copilot CLI — the standalone executable copilot, distributed as the npm package @github/copilot.
release-validation
Validates the next MeshLLM release against the last GitHub release on approved real hosts and produces a formal evidence-backed readiness report.