reviewer-protocol

reviewer-protocol is a skill for Claude Code from gustavo-meilus/superpipelines. It costs 33 tokens per session (1,229 once invoked), scanned A, original, MIT.

An internal review protocol for checking findings from an automated code analysis pipeline.

In plain words
What is it for?
It helps validate issue counts, required fields, and coverage of null checks, error handling, and naming problems.
Why use it?
It gives the reviewer consistent checks for missing, malformed, or incomplete findings before a report is produced.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

Part of the superpipelines plugin — 54 skills, 10 commands, 14 agents, 4 hooks shipped together

Good fit It helps validate issue counts, required fields, and coverage of null checks, error handling, and naming problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gustavo-meilus/superpipelines/reviewer-protocol
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.

Any agent
npx skills add gustavo-meilus/superpipelines --skill reviewer-protocol
Clone the repo
git clone --depth 1 https://github.com/gustavo-meilus/superpipelines

Made for: Claude Code.

Or install superpipelines, the plugin that ships this one along with the rest of its 54 skills, 10 commands, 14 agents, 4 hooks.

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 reviewer-protocol

README.md
[![agentmods](https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/reviewer-protocol/github.svg)](https://agentmods.dev/skills/gustavo-meilus/superpipelines/reviewer-protocol)
Your own site
<a href="https://agentmods.dev/skills/gustavo-meilus/superpipelines/reviewer-protocol"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/reviewer-protocol/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.

agentmods 80×15 button for reviewer-protocol

Your own site · 80×15
<a href="https://agentmods.dev/skills/gustavo-meilus/superpipelines/reviewer-protocol"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/reviewer-protocol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,229 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 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 5.1 $0.00033 $0.01229
Opus 5 $0.00016 $0.00615
Sonnet 5 $0.00007 $0.00246
Haiku 4.5 $0.00003 $0.00123

Measured 10d ago against content hash 5f5de62d7db7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

reviewer-protocol 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 10d 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.

.agents/skills/superpipelines/parity-test-f/reviewer-protocol/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer — Operational Protocol

Protocol

1. DISCOVER

  1. Read inputs from the orchestrator dispatch context:
    • findings_path: path to findings.json written by the analyzer.
    • run_id: current run identifier.
    • root: resolved scope root.
  2. Verify findings_path exists and is valid JSON. If the file does not exist: emit BLOCKED with message: "Analyzer findings not found at {findings_path}. The analyzer step may have failed."
  3. Parse the findings JSON. If JSON is malformed: emit BLOCKED with message: "Analyzer findings at {findings_path} are not valid JSON. Re-run the analyzer step."

2. PROCESS

Validate the findings for completeness and correctness:

  1. Structural validation:

    • Verify findings.issue_count matches findings.issues.length. If not: record a reviewer note that the count is inconsistent and lower completeness_score by 0.1.
    • Verify each issue entry has category, severity, location, and description fields. Issues missing required fields are flagged as incomplete.
  2. Category coverage:

    • Identify which of the three expected categories (null_check, error_handling, naming) have at least one finding. Record missing_categories as any category with zero findings.
    • A missing category is not automatically a rejection — it may be genuinely absent from the diff. However, if all three categories are missing and issue_count > 0, flag as suspicious and lower completeness_score by 0.2.

Read the full file on GitHub · 89 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. 10d ago First seen · 89 lines · 33 tokens per session scan A 5f5de62d7db7

Subscribe to this mod's changes

reviewer-protocol is a skill published in the GitHub repository gustavo-meilus/superpipelines (4 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,229 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 2026-08-31.

Related

Other skills, from other repositories

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-review-patterns

Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.

a5c-ai/babysitter · 33 tokens

code-review-pipeline

Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.

a5c-ai/babysitter · 28 tokens

subagent-driven-development

Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per task.

a5c-ai/babysitter · 26 tokens

verification

Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.

a5c-ai/babysitter · 25 tokens