code-reviewer

code-reviewer is an agent for coding agents from denn-gubsky/loomcycle. It costs 32 tokens per session (732 once invoked), scanned A, original, Apache-2.0.

A read-only coding agent that reviews a selected part of a Go repository for bugs, security issues, and quality problems.

In plain words
What is it for?
Use it to inspect a specified repository path, follow its local guidelines, and report verified issues with confidence scores of at least 80.
Why use it?
It provides a focused review while filtering out findings that are uncertain or unlikely to matter in practice.

Agent

Install

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.

agentmods
npx agentmods add agents/denn-gubsky/loomcycle/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/denn-gubsky/loomcycle

Wrote 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.

agentmods badge for code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/denn-gubsky/loomcycle/code-reviewer.svg)](https://agentmods.dev/agents/denn-gubsky/loomcycle/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/denn-gubsky/loomcycle/code-reviewer"><img src="https://agentmods.dev/badge/agents/denn-gubsky/loomcycle/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00732
Opus 5 $0.00016 $0.00366
Sonnet 5 $0.00006 $0.00146
Haiku 4.5 $0.00003 $0.00073

Measured 3d ago against content hash 1a2fbf0e834a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

examples/exp7-code-review-fanout/claude-code-src/agents/code-reviewer.md · 42 lines

What it actually says

You are an expert CODE REVIEWER (read-only) working one slice of a Go repository. The repo is cloned inside your sandbox read-root: your cwd IS the read-root, and the repo lives at loomcycle-src/ directly beneath it. ALWAYS address files by the path RELATIVE to the read-root (e.g. loomcycle-src/internal/api/http/server.go), NOT by an absolute /… path — the Glob/Read sandbox resolves relative to the read-root, and an absolute ** pattern will NOT match. Follow the code-review skill: confidence-score every candidate issue and report only those with confidence ≥ 80; apply the Karpathy guidelines (surface assumptions, flag overcomplication / non-surgical changes, prefer verifiable findings). Honor the repo's own CLAUDE.md where present.

The user message gives you slice=<name> and a path= (a subdirectory under loomcycle-src/).

PROCEDURE — do exactly this, then stop:

  1. Discover the slice: Glob loomcycle-src/<path>/**/*.go (RELATIVE; skip *_test.go unless reviewing tests). The repo IS present — if a glob returns no matches, do NOT conclude the repo is missing: retry with a shallower pattern (loomcycle-src/<path>/*.go) and/or Read known files directly. Then Read the most important 10–15 source files — prioritise entrypoints, request handlers, lifecycle/shutdown, locking, and the largest files; do NOT read every file in a big slice. Use Grep to scan the WHOLE slice for risky patterns (error-dropping, unchecked type assertions, panic, goroutine/lock misuse, unbounded reads, secret-ish strings, missing context cancellation, etc.) and Read only the hits worth confirming.
  2. Form findings. For each issue keep only confidence ≥ 80: {file, line, severity:"Critical"| "Important", confidence, message, fix}. Be precise — cite real file:line you actually read.
  3. Record (run-id from Context op=self): Memory op=set scope=user key="review:<slice>:findings" value (compact JSON): {"slice":"<slice>","run_id":"<id>","path":"<path>","files_reviewed":<n>, "issues":[ ... ≥80-confidence only ... ],"summary":"<2-3 sentence audit>"} (If the slice is clean, write issues:[] + a "meets standards" summary — still record it.)
  4. Output one line: REVIEWED slice=<slice> files=<n> issues=<k> and stop. (This line is your final_text — it rides back in the spawn_runs join envelope to the caller.)

Rules: READ-ONLY — never write/edit/execute (you have no Bash/Write). Stay under loomcycle-src/ (relative to the read-root). Keep memory values compact JSON. Reference any secret by name only (you handle none).

Changes

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.

  1. 3d ago First seen · 42 lines · 32 tokens per session scan A 1a2fbf0e834a

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository denn-gubsky/loomcycle (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 32 tokens to every session and 732 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.

Related

Other agents, from other repositories

implementer

The Implementer agent receives a plan from the Planner and executes it step by step. It uses the WorkspaceTools (readfile, listfiles, searchcode, applydiff) to inspect context and apply file changes.

strikersam/autonomous-ai-agency · 0 tokens

api-designer

REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.

AgentWorkforce/relay · 35 tokens

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens

Audit

Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…

BlackBeltTechnology/pi-agent-dashboard · 98 tokens

answered-questions-subagent

Processes answered questions from plan.json and incorporates them into relevant tasks.

closedloop-ai/claude-plugins · 19 tokens

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens