A security-fix helper that creates small, testable code changes for confirmed vulnerabilities. It also turns each proof-of-concept demonstration into a regression test, which checks that the flaw stays fixed.

It applies fixes for several vulnerability categories, checks all affected call sites, reviews the patch for unintended effects, and produces a unified diff and regression tests.

It reduces the risk of incomplete patches, missed vulnerable code paths, or fixes that introduce a new timing-related bug.

mcp2agy-fix — Skill for Claude Code and Codex by uziii2208: A security-fix helper that creates small, testable code changes…

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/uziii2208/mcp2agy/fix

Any agent

npx skills add uziii2208/mcp2agy --skill fix

Clone the repo

git clone --depth 1 https://github.com/uziii2208/mcp2agy

Made for: Claude Code, Codex.

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,560 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.

Model	Per session	Once invoked
Fable 5	$0.00089	$0.01560
Opus 5	$0.00044	$0.00780
Sonnet 5	$0.00018	$0.00312
Haiku 4.5	$0.00009	$0.00156

Measured 2d ago against content hash b535193b089c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp2agy-fix 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/plugins/mcp2agy/skills/fix/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fix — Security Code Remediation & Subagent (v3.0.0)

0. Prime Directive & Remediation Principles

The Fixer produces patches that are minimal, correct, and provably effective:

Multi-Site Completeness: Patch EVERY vulnerable call site in the project, not just the one hit by the PoC.
Atomicity Check: Ensure the fix does NOT introduce a new TOCTOU race condition (e.g. check-then-act os.path.exists before open instead of O_CREAT | O_EXCL).
No Scope Creep: Change ONLY what is required to remediate the vulnerability. Do not refactor unrelated code.
PoC-as-Regression-Test: Convert the Verifier's PoC into a permanent automated unit test that passes with the patch and fails without it.

Operating Modes:

Subagent Mode (Delegated by Orchestrator):
- Consumes verified_findings.yaml from mcp2agy_workspace/auditor_zone/results/<run_id>/.
- Generates minimal diff at mcp2agy_workspace/auditor_zone/results/<run_id>/fixes.diff.
- Generates regression test harnesses in mcp2agy_workspace/auditor_zone/results/<run_id>/regression_tests/.
- Responds to the Orchestrator with patch metrics.
Standalone Mode (CLI /fix <finding_yaml>):
- Generates patch and test harness for individual finding.

⚠️ CRITICAL: MCP Tool Usage Policy

NEVER call call_mcp_tool() or any MCP server tools directly when running as a subagent. MCP tools (e.g., generate_fix, check_fix_completeness, list_fix_templates) are lazy-loaded and require interactive user approval. When a subagent calls an MCP tool, it blocks indefinitely.

Instead, generate fixes using native tools:

view_file — Read verified findings, source code, and evidence
replace_file_content — Apply minimal code patches
write_to_file — Generate regression test harnesses and diff files
grep_search — Find all call sites for multi-site completeness
run_command — Run tests and verify fixes

If the Orchestrator has pre-gathered MCP tool data, it will be provided in your invocation prompt.

Read the full file on GitHub · 146 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.

2d ago First seen · 146 lines · 89 tokens per session scan A b535193b089c

Subscribe to this mod's changes

mcp2agy-fix is a skill published in the GitHub repository uziii2208/mcp2agy (1 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 1,560 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.

Security Testing

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