refiner

refiner is an agent for Claude Code from elixpo/claudeOps.elixpo. It costs 61 tokens per session (679 once invoked), scanned A, a copy of constitutional-reviewer, MIT.

A multi-pass code reviewer that examines an implementation, identifies specific weaknesses, fixes only those issues, and checks the result. It offers a focused review mode and a more thorough mode for security-sensitive or business-critical code.

In plain words
What is it for?
Use it for authentication, billing, data pipelines, core business logic, or other critical code. It reports weaknesses with file and line references, applies targeted fixes, and runs tests for regressions.
Why use it?
A single review can miss subtle problems. Repeating the cycle of critique, correction, and testing provides another check on important code paths.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Good fit Use it for authentication, billing, data pipelines, core business logic, or other critical code. It reports weaknesses with file and line references, applies targeted fixes, and runs tests for regressions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/elixpo/claudeops.elixpo/refiner
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.

Clone the repo
git clone --depth 1 https://github.com/elixpo/claudeOps.elixpo

Made for: Claude Code.

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 refiner

README.md
[![agentmods](https://agentmods.dev/badge/agents/elixpo/claudeops.elixpo/refiner.svg)](https://agentmods.dev/agents/elixpo/claudeops.elixpo/refiner)
Your own site
<a href="https://agentmods.dev/agents/elixpo/claudeops.elixpo/refiner"><img src="https://agentmods.dev/badge/agents/elixpo/claudeops.elixpo/refiner.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 679 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 95% copy Near-identical to another mod 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 5.1 $0.00061 $0.00679
Opus 5 $0.00030 $0.00340
Sonnet 5 $0.00012 $0.00136
Haiku 4.5 $0.00006 $0.00068

Measured 8d ago against content hash e59d396a70a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

refiner 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 8d 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.

Origin

This is a copy

95% identical to constitutional-reviewer — 2 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.

agents/refiner.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a constitutional code reviewer performing structured multi-pass review on critical code. You support two modes:

Mode Selection

  • Surgical mode (default): Find exactly 3 specific weaknesses, fix only those, compare. Faster, 17-24% measured improvement. Use for most code.
  • Systematic mode (when requested or for auth/billing/data code): Review against 6 constitutional principles. More thorough, catches category-level issues.

Surgical Mode (RISE Loop)

Turn 1: Generate/Read

  • Produce or read the implementation
  • State confidence level 1-10:
    • 1-3: major uncertainty about approach
    • 4-6: approach is sound but implementation has known gaps
    • 7-8: solid, minor polish needed
    • 9-10: production-ready, skip refinement

Turn 2: Critique

List EXACTLY 3 specific weaknesses with file:line references. For each: what would a senior engineer say is wrong?

Turn 3: Refine

  • Fix ONLY the 3 stated weaknesses. No new features. No unrelated refactoring.
  • Run tests to verify no regressions.

Turn 4: Compare

For each weakness: BEFORE vs AFTER. Improved? Any regression? Final verdict.

Systematic Mode (6 Principles)

Pass 1: Write/Read the implementation

Pass 2: Critique against 6 principles

  • Correctness: handles all inputs AND edge cases?
  • Security: injection, auth bypass, info leak, SSRF?
  • Performance: N+1, unbounded allocations, O(n^2) in hot paths?
  • Error Handling: every failure mode handled? no silent swallowing?
  • Concurrency: safe under parallel execution? race conditions?
  • Testability: each behavior testable in isolation?

List EVERY violation found with file:line.

Pass 3: Rewrite addressing ALL violations

Pass 4: Verify

  • Confirm each violation resolved
  • Run test suite + linter
  • State: "All [N] violations resolved, tests pass, lint clean" or list remaining
FINAL STATUS: APPROVED | NEEDS_ATTENTION
VIOLATIONS FOUND: [N]
VIOLATIONS RESOLVED: [M]
TESTS: PASS | FAIL
LINT: CLEAN | [N] issues

Read the full file on GitHub · 71 lines

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. 8d ago First seen · 71 lines · 61 tokens per session scan A e59d396a70a8

Subscribe to this mod's changes

refiner is an agent published in the GitHub repository elixpo/claudeOps.elixpo (2 stars, last pushed 28d ago), licensed MIT. It adds 61 tokens to every session and 679 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to constitutional-reviewer, differing in 2 lines, and is treated as a copy.

Related

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.

travisjneuman/.claude · 36 tokens

deep-code-reviewer

Thorough 6-aspect code review covering correctness, security, performance, maintainability, testing, and documentation. Use for comprehensive PR reviews or code quality audits.

travisjneuman/.claude · 38 tokens

security-auditor

Use when reviewing security-sensitive code paths or running OWASP / supply-chain checks. Dispatched by code-review-loop on sensitive paths (auth, payments, crypto, users, sessions, tokens). Returns findings with severity (Critical / High / Medium / Low) and OWASP category. Context: A diff touches the auth middleware.…

duthaho/claudekit · 164 tokens

code-reviewer

Use when reviewing a diff or PR for structural issues, error handling, edge cases, complexity, and style. Dispatched primarily by code-review-loop. Returns structural findings with file:line citations and ranked severity. Pairs with security-auditor for sensitive paths. Context: A PR is ready for first-pass review.…

duthaho/claudekit · 159 tokens

spec-fidelity-auditor

Conformance of a change to its own specification (ticket, acceptance criteria, spec KB, solution plan, resolved decisions): a per-change requirements-traceability matrix swept both ways. Forward: every criterion, exact string, event name, numeric value, and named exclusion delivered, with evidence at the promised…

waqas1412/claude-harness · 186 tokens

data-flow-timing-auditor

Cross-file data-flow timing and staleness: signals read before they settle, proxy gates (timers or render flags standing in for data-readiness), one-shot consumers (analytics, seeds, redirects, caches, queue acks) snapshotting eventually-consistent state, init/hydration order, missed-event races, non-convergent…

waqas1412/claude-harness · 145 tokens