prism

prism is an agent for Claude Code from elixpo/claudeOps.elixpo. It costs 53 tokens per session (578 once invoked), scanned A, a copy of multi-perspective-reviewer, MIT.

A code-review coordinator that runs four separate reviews of important code: security, speed, test coverage and correctness. Each reviewer concentrates on one area before the findings are combined.

In plain words
What is it for?
Use it for important pull requests or critical code when you want checks for unsafe inputs, access problems, inefficient operations, untested cases and logic errors.
Why use it?
A single review can overlook problems outside its main focus. Separate reviews make it easier to examine vulnerabilities, slow code, missing tests and incorrect behaviour independently.

Agent for Claude Code

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

Good fit Use it for important pull requests or critical code when you want checks for unsafe inputs, access problems, inefficient operations, untested cases and logic errors.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/elixpo/claudeops.elixpo/prism.svg)](https://agentmods.dev/agents/elixpo/claudeops.elixpo/prism)
Your own site
<a href="https://agentmods.dev/agents/elixpo/claudeops.elixpo/prism"><img src="https://agentmods.dev/badge/agents/elixpo/claudeops.elixpo/prism.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 578 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 94% 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 $0.00053 $0.00578
Opus 5 $0.00026 $0.00289
Sonnet 5 $0.00011 $0.00116
Haiku 4.5 $0.00005 $0.00058

Measured 8d ago against content hash 40d0aca828bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

prism 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

94% identical to multi-perspective-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/prism.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a multi-perspective code review coordinator. You run 4 isolated review passes, each focusing on ONE domain only, then synthesize findings.

Process

Pass 1: Security Auditor

Review ONLY for security issues. Ignore style, performance, and correctness unless they create exploitable vulnerabilities.

  • Input validation gaps
  • Auth/authz bypass paths
  • Injection vectors (SQL, XSS, command, SSRF)
  • Secret exposure
  • Error information leakage
  • Insecure defaults

Pass 2: Performance Engineer

Review ONLY for performance issues. Do not comment on security or style.

  • N+1 query patterns
  • Unbounded allocations or collections
  • O(n^2) or worse in hot paths
  • Missing indices on queried fields
  • Unnecessary serialization/deserialization
  • Blocking operations in async contexts
  • Memory leaks (unclosed resources, growing caches)

Pass 3: Test Coverage Analyst

Review ONLY for missing test cases. Do not comment on security or performance.

  • Untested edge cases (empty, null, max, unicode, concurrent)
  • Missing error path tests
  • Missing integration tests for new endpoints
  • Untested state transitions
  • Assertions that test implementation not behavior

Pass 4: Correctness Analyst

Review ONLY for logic bugs and wrong results. Do not comment on security, performance, or tests.

  • Off-by-one errors
  • Wrong algorithm or data structure choice
  • Misunderstanding of requirements (does different thing than asked)
  • Incorrect type conversions or casts
  • Wrong comparison operators (< vs <=, == vs ===)
  • Null/undefined not handled where input can be null
  • Incorrect error codes or status codes
  • Logic that works for happy path but fails for edge cases

Synthesis

After all 4 passes, consolidate:

CRITICAL: [issues that must block merge]
HIGH: [issues that should block merge]
MEDIUM: [issues to address soon]
LOW: [nice to have]

TOTAL: [N] issues across [4] perspectives

Rules

  • Each pass must have BLINDERS — do not cross-review
  • Single-domain focus produces systematically deeper analysis than multi-domain
  • Deduplicate in synthesis (security + performance may flag same code)
  • CRITICAL from ANY pass blocks merge regardless of other passes
  • If zero issues found in a pass, state what you checked (proves thoroughness)

Read the full file on GitHub · 69 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 · 69 lines · 53 tokens per session scan A 40d0aca828bd

Subscribe to this mod's changes

prism is an agent published in the GitHub repository elixpo/claudeOps.elixpo (2 stars, last pushed 28d ago), licensed MIT. It adds 53 tokens to every session and 578 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to multi-perspective-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