cpv-batch-fix-protocol

cpv-batch-fix-protocol is a skill for Claude Code, Codex from Emasoft/claude-plugins-validation. It costs 82 tokens per session (1,764 once invoked), scanned A, original, MIT.

A schema reference for a protocol that divides plugin fixes into separate work units and combines their results. It documents the files and status data exchanged by the planner, helper agents, and aggregator.

In plain words
What is it for?
Use it when implementing or extending consumers of the batch-fix protocol, including shard plans, per-shard manifests, and per-shard status files.
Why use it?
It prevents different parts of a parallel fixing workflow from disagreeing about file formats or responsibilities. It also explains when splitting work is appropriate.

Skill for Claude CodeCodex

Part of the claude-plugins-validation plugin — 31 skills, 14 commands, 14 agents shipped together

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 skills/emasoft/claude-plugins-validation/cpv-batch-fix-protocol
Any agent
npx skills add Emasoft/claude-plugins-validation --skill cpv-batch-fix-protocol
Clone the repo
git clone --depth 1 https://github.com/Emasoft/claude-plugins-validation

Made for: Claude Code, Codex.

Or install claude-plugins-validation, the plugin that ships this one along with the rest of its 31 skills, 14 commands, 14 agents.

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 cpv-batch-fix-protocol

README.md
[![agentmods](https://agentmods.dev/badge/skills/emasoft/claude-plugins-validation/cpv-batch-fix-protocol.svg)](https://agentmods.dev/skills/emasoft/claude-plugins-validation/cpv-batch-fix-protocol)
Your own site
<a href="https://agentmods.dev/skills/emasoft/claude-plugins-validation/cpv-batch-fix-protocol"><img src="https://agentmods.dev/badge/skills/emasoft/claude-plugins-validation/cpv-batch-fix-protocol.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,764 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 $0.00082 $0.01764
Opus 5 $0.00041 $0.00882
Sonnet 5 $0.00016 $0.00353
Haiku 4.5 $0.00008 $0.00176

Measured 3d ago against content hash 2bd097a50e48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cpv-batch-fix-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 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.

skills/cpv-batch-fix-protocol/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cpv-batch-fix-protocol

Overview

/cpv-batch-fix slices a plugin's validation findings into parallel-fix shards and dispatches N cpv-plugin-fixer-agent agents from the main session — one per shard, each with a fresh context window whose size depends on cpv-plugin-fixer-agent.model (per-model — never assume a fixed limit). This skill documents the data contract that ties the planner, the shard agents, and the aggregator together. Loaded by cpv-plugin-fixer-agent (when it sees mode: batch_shard in its context block) and by the /cpv-batch-fix slash command body.

See JSON schemas for the three file formats and TRDD-71e68ab5 (design/tasks/TRDD-20260519_114050+0200-71e68ab5-batch-fix-parallel-sharding.md) for the design rationale.

  1. Top-level index (index.json) · 2. Per-shard manifest (shard-K.json) · 3. Per-shard status (shard-K.status.json) · Schema version bumps

Fork vs fresh worker — the token-honest dispatch choice (TRDD-GVMOKJBB)

Fan-out is a LAST resort, not a default (cost ≈ turns × per-turn-context):

  1. One plugin that fits one context → NO fan-out. Sequential fix-as-you-go in ONE lean fixer (read each file once, fix in the same turn) is cheapest — a single warm context reused. Forking merely for parallelism here costs N× the context (a wall-clock tradeoff, NOT a token saving).
  2. A plugin that EXCEEDS one context → fan out, and pick the worker by the dispatcher:
    • subagent_type:"fork" (Agent tool) — ONLY from a LEAN dispatcher that already loaded the exact context the worker needs (the fix skill + the ledger). A fork inherits the dispatcher's WHOLE conversation at cache-read rate, so it pays off only when that conversation is small and relevant. NEVER fork the bloated main session (it carries all of main's skills/MCP/CLAUDE.md forward).
    • Fresh lean worker + on-disk slice — the correct choice from a bloated/cold context. The /cpv-batch-fix path spawns N cpv-plugin-fixer-agents from the MAIN session, so this is the batch default: hand each worker its shard manifest / ledger slice ON DISK (a file path, not context inheritance) with a curated tool surface (no MCP).
  3. NEVER a skill context: fork. That runs a skill in an ISOLATED fresh subagent with no conversation history (docs: skills#run-skills-in-a-subagent) → it COLD-writes cache = wastes tokens. It is the OPPOSITE of the Agent-tool fork despite the shared word.

Read the full file on GitHub · 109 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 109 lines · 82 tokens per session scan A 2bd097a50e48

Subscribe to this mod's changes

cpv-batch-fix-protocol is a skill published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 1,764 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens