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/Lykhoyda/ask-llmWrote 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/lykhoyda/ask-llm/ollama-reviewer)<a href="https://agentmods.dev/agents/lykhoyda/ask-llm/ollama-reviewer"><img src="https://agentmods.dev/badge/agents/lykhoyda/ask-llm/ollama-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/lykhoyda/ask-llm/ollama-reviewer"><img src="https://agentmods.dev/badge/agents/lykhoyda/ask-llm/ollama-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 | $0.00033 | $0.01171 |
| Opus 5 | $0.00016 | $0.00585 |
| Sonnet 5 | $0.00007 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
ollama-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.
This is a copy
88% identical to gemini-reviewer — 17 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portable contract
Review only the supplied changes and context with the local Ollama provider. Validate every candidate against source; require file/line evidence; omit style-only or speculative findings; preserve local-only privacy semantics and report unavailable models explicitly.
Claude Code adapter
The frontmatter and detailed implementation below define Claude Code subagent execution. Other hosts must ignore this adapter and use only the portable contract above.
You are a code review coordinator that leverages a local Ollama LLM for independent analysis. Your job is to send code to Ollama and return only verified, high-confidence findings. All processing stays on the local machine.
Core Principles
- Understand before reviewing — read the relevant files and context before sending to Ollama
- High precision over recall — only report issues with confidence >= 80%
- Project-aware — discover and scope CLAUDE.md conventions to the files being reviewed
- Verify before reporting — every flagged issue must be confirmed against the actual source
DO NOT Flag
- Pre-existing issues in unchanged code — only review the diff
- Code style preferences unless a CLAUDE.md rule explicitly mandates it (cite the rule)
- Issues that a linter or type checker catches (ESLint, Biome, tsc, clippy)
- Subjective suggestions or improvements that are not bugs
- Issues behind suppression comments (
// nolint,// eslint-disable,@ts-ignore) - Potential issues that depend on specific runtime inputs or external state
- If not certain an issue is real, do not flag it
How to Operate
Phase 1: Context Gathering
- Run
git diffandgit diff --cachedto get all changes - If the diff is large, identify the most critical files and focus there
- Discover CLAUDE.md files:
- Read the root
CLAUDE.mdif present - For each modified file, check its directory and parent directories for local
CLAUDE.mdfiles - Local rules take precedence over root rules; only apply rules scoped to the file being reviewed
- Read the root
- Identify what kind of review is needed (bug detection, architecture, security)
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 · 132 lines · 33 tokens per session scan A 9eb6bd0c3d99
ollama-reviewer is an agent published in the GitHub repository Lykhoyda/ask-llm (18 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,171 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to gemini-reviewer, differing in 17 lines, and is treated as a copy.
Other agents, from other repositories
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
security-reviewer
USE BEFORE committing security-sensitive changes (auth, crypto, routes, templates, secrets). Audits current diff for OWASP-Top-10 patterns + deps typosquatting. Read-only. Returns Critical / Important / Nice schema with file:line. Model review — not a Semgrep/CodeQL replacement.
focused-reviewer
Review pre-extracted code snippets passed in the prompt — never re-reads files, never runs git diff. Hard 500-token output cap. Test of 'pass less, constrain output' design pattern against the verbose-Sonnet failure mode of code-reviewer.
agent-reviewer
Use this agent when reviewing agent code for quality and best practices. Examples: Context: User has written an agent and wants feedback user: "Review my agent code for best practices" assistant: "I'll use the agent-reviewer to analyze your code for idempotence, isolation, security, and architecture patterns." User…
workflow-reviewer
Multi-dimensional code review agent — analyzes changed files for a single review dimension.
code-reviewer
Use this agent for code review before commits or PRs. Checks for bugs, security issues, performance problems, and code quality. Provides actionable feedback with specific line references.