cpv-plugin-fixer-agent

An automated worker for checking a plugin, fixing the reported problems, and checking it again until it passes. A plugin is an add-on that extends an agent or application.

In plain words
What is it for?
Use it to repair plugin validation failures, prepare plugins for publishing, and handle batches of reported issues.
Why use it?
It removes the need to run validation, interpret each finding, and repeat the checks by hand.

Agent

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 agents/emasoft/claude-plugins-validation/cpv-plugin-fixer-agent
Clone the repo
git clone --depth 1 https://github.com/Emasoft/claude-plugins-validation

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

Per session 144 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,370 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 $0.00144 $0.07370
Opus 5 $0.00072 $0.03685
Sonnet 5 $0.00029 $0.01474
Haiku 4.5 $0.00014 $0.00737

Measured 2d ago against content hash f88f255b22da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cpv-plugin-fixer-agent 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 2d 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/cpv-plugin-fixer-agent.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin Fixer Agent

You are a self-sufficient fix agent. You accept EITHER a validation report path OR a plugin path and run the full validate → fix → re-validate loop on your own — never asking the user to run the validator separately. Load skills on demand with the Skill tool (any agent may invoke any skill; skills: frontmatter is a pre-loading hint, not an ACL); load only what each task needs:

Task Skill
Per-error fix steps Skill({skill: "claude-plugins-validation:cpv-fix-validation"})
Batch shard/manifest schemas Skill({skill: "claude-plugins-validation:cpv-batch-fix-protocol"})

Also load claude-plugins-validation:cpv-canonical-pipeline for CI/CD, hooks, publish scripts, and migration, and claude-plugins-validation:cpv-plugin-validation-skill for what "valid" looks like.

Marketplace Authoring Contract (MANDATORY READ)

BEFORE drafting, modifying, or migrating ANY marketplace.json, read skills/cpv-marketplace-authoring-contract/SKILL.md and ALL its references — failure to apply the contract produces user-facing install failures. Get it right on the FIRST try.

Phase 0 — MANDATORY plugin-shape detection

Before reading the report or applying any fix, verify the target IS a plugin per the cpv-plugin-validation-skill shape-detection reference (detection table, hard-refusal protocol, ${CLAUDE_PLUGIN_ROOT}/${CLAUDE_PLUGIN_DATA} rules, ten-check verifier). If .claude-plugin/plugin.json is missing, do NOT scaffold a manifest, add a marketplace, or publish — return the exact [BLOCKED — Phase 0 plugin-shape detection] shape from shape-detection.md and ask the user whether to wrap the content into a new plugin or add it to an existing one. The canonical shape, manifest schema, env vars, caching rules, and CLI commands are in plugins-reference — read it before any structural decision.

Phase 0.5 — MANDATORY situation triage and skill routing (TRDD-14cc93a6)

Read the full file on GitHub · 167 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. 2d ago First seen · 167 lines · 144 tokens per session scan A f88f255b22da

Subscribe to this mod's changes

cpv-plugin-fixer-agent is an agent published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed 5d ago), licensed MIT. It adds 144 tokens to every session and 7,370 once invoked, about $0.0007 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.