An automated coding agent for fixing a software security flaw known as a CVE, which is a publicly identified vulnerability in a program or library.

Use it after a vulnerability has been researched to make the smallest version change, verify it, create a branch and commit, and open a pull request.

It handles the repeatable work of applying a researched version update, rebuilding the project, checking tests, and preparing the code change for review.

vuln-fixer — Agent for Claude Code by ihudak

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add ihudak/ihudak-claude-plugins

Claude Code

/plugin install dev-workflows

Made for: Claude Code.

Or install dev-workflows, the plugin that ships this one along with the rest of its 5 commands, 12 agents, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/vuln-fixer/github.svg)](https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/vuln-fixer)

Your own site

<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/vuln-fixer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/vuln-fixer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/vuln-fixer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/vuln-fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 122 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,531 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.

Model	Per session	Once invoked
Fable 5.1	$0.00122	$0.02531
Opus 5	$0.00061	$0.01265
Sonnet 5	$0.00024	$0.00506
Haiku 4.5	$0.00012	$0.00253

Measured today against content hash 209d05e317ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

vuln-fixer 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 today.

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.

plugins/dev-workflows/agents/vuln-fixer.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core references. A citation of the form workflows-core:<name> names a shared reference in the workflows-core plugin. Load it with Skill(skill: "workflows-core:reference", args: "<name>") — never by path: ${CLAUDE_PLUGIN_ROOT} resolves to this plugin, which does not carry it.

vuln-fixer — CVE Fix Agent

Read ${CLAUDE_PLUGIN_ROOT}/references/handoff/vuln-fixer.md for the exact input/output document format. Read ${CLAUDE_PLUGIN_ROOT}/references/fix-vuln/build-systems.md for per-ecosystem update commands. Read ${CLAUDE_PLUGIN_ROOT}/commands/vuln.md sections "Git Workflow" and "Handling Test Failures" for branch naming and the regression protocol. The commit message and PR format documented there are the orchestrator's to apply in Step 3.9 — read them for context, never act on them. Read ${CLAUDE_PLUGIN_ROOT}/references/handoff/test-baseliner.md for the test-baseliner handoff format.

Process

Receive the research report for one CVE with status: READY. The report may be provided inline or as an absolute file path — Read the file first when given a path.

On a read failure, follow the read-failure contract in ${CLAUDE_PLUGIN_ROOT}/references/context-management.md — the research report is an evidence input: hard stop, return status: BLOCKED naming the unreadable path, and never re-research the CVE to reconstruct it.

Phase resume. If the input includes phase: verify-resume, skip steps 1 through 4 — the baseline was captured (by the orchestrator), the branch was created, the fix was applied, and the build was run on the prior invocation. Resume at step 5 (Verify), using the baseline_tests: provided + baseline_passing

baseline.passing_tests re-supplied by the orchestrator in the input. Do not re-baseline (that would clobber the pre-fix snapshot) and do not re-apply the version pin. Default phase (omitted or phase: full) runs all steps.

If the input includes phase: regression-resume, skip steps 1-5 — jump straight to "Test regression" step 4 below, honoring the regression_decision: keep-anyway | revert supplied by the orchestrator.

When gate_tests_on_review: true is set on a phase: full call, the orchestrator is required to capture and pass the baseline itself (see /vuln command Step 3); under that gate, baseline_tests: run-fresh is invalid because the captured baseline cannot survive the AWAITING_REVIEW boundary.

Read the full file on GitHub · 148 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.

today Changed · +2 lines 209d05e317ff
4d ago Changed · +29 lines · +33 tokens per session 8cad85f7b0a2
9d ago First seen · 117 lines · 89 tokens per session scan A 72eaed96b358

Subscribe to this mod's changes

vuln-fixer is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 2,531 once invoked, about $0.0006 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.

Claude Code Debugging Security ai-agents ai-code-review claude-code-plugins developer-productivity documentation-automation

do-debugger

Autonomous Durable Objects debugger. Automatically detects and fixes DO configuration errors, runtime issues, and common mistakes without user intervention.

secondsky/claude-skills · 28 tokens

queue-debugger

Use this agent when the user encounters "queue not delivering messages", "consumer errors", "DLQ filling up", "throughput issues", "message backlog", "queue timeout errors", or needs systematic Cloudflare Queues troubleshooting. Examples.

secondsky/claude-skills · 0 tokens

Turnstile CSP Debugger

This agent should be used when the user asks to "validate CSP for turnstile", "fix CSP errors", "check content security policy", or encounters error 200500. Analyzes Content Security Policy headers and suggests Turnstile-compatible configurations.

secondsky/claude-skills · 58 tokens

cors-debugger

Use this agent when the user encounters "CORS errors", "browser upload fails", "access-control-allow-origin", "CORS policy blocked", or needs CORS troubleshooting. Examples.

secondsky/claude-skills · 0 tokens

discovery-reliability-reviewer

Discovery-time reliability + operability ONLY — a forked-context, read-only reviewer for discovery artifacts (the journey map, service blueprint, screen flows, architecture, decision brief). Required at the discovery loop's G2 reconcile. A DISTINCT agent from work-loop's code quality-engineer — it reviews the design's…

eugenelim/agent-ready-repo · 120 tokens

debugger

Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.

sgaunet/claude-plugins · 23 tokens