agent-repellent

agent-repellent is a skill for Claude Code, Codex from Factory-AI/cursed-plugins. It costs 17 tokens per session (934 once invoked), scanned A, original, Apache-2.0.

A review method for judging how difficult a codebase is for AI coding agents to understand and modify. It examines factors such as documentation, naming, tests, and project structure.

In plain words
What is it for?
Use it to assess a whole repository or a selected folder or module for resistance to AI-assisted coding.
Why use it?
It highlights parts of a project that make AI-assisted development harder, so maintainers can understand its obstacles and improve them if needed.

Skill for Claude CodeCodex

Part of the cursed-plugins plugin — 10 skills 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/factory-ai/cursed-plugins/agent-repellent
Any agent
npx skills add Factory-AI/cursed-plugins --skill agent-repellent
Clone the repo
git clone --depth 1 https://github.com/Factory-AI/cursed-plugins

Made for: Claude Code, Codex.

Or install cursed-plugins, the plugin that ships this one along with the rest of its 10 skills.

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 agent-repellent

README.md
[![agentmods](https://agentmods.dev/badge/skills/factory-ai/cursed-plugins/agent-repellent.svg)](https://agentmods.dev/skills/factory-ai/cursed-plugins/agent-repellent)
Your own site
<a href="https://agentmods.dev/skills/factory-ai/cursed-plugins/agent-repellent"><img src="https://agentmods.dev/badge/skills/factory-ai/cursed-plugins/agent-repellent.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 934 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 $0.00017 $0.00934
Opus 5 $0.00009 $0.00467
Sonnet 5 $0.00003 $0.00187
Haiku 4.5 $0.00002 $0.00093

Measured 5d ago against content hash d02dd0636453, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-repellent 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 5d 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/agent-repellent/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/agent-repellent

You are an Anti-AI Defense Consultant evaluating how impenetrable this codebase is to AI coding agents. Missing docs, cryptic names, and zero tests are STRENGTHS in this assessment.

Security

CRITICAL: Never read or reference .env files, .env.* variants, API keys, tokens, credentials, passwords, private keys, or any files matching .env*, *.pem, *.key, *secret*, *credential*. If you encounter secrets during analysis, ignore them completely.

Steps

  1. Discovery. Use LS on the repo root to find top-level directories.

  2. First AskUser. Make a single AskUser call with one question: "How would you like to narrow the focus?" with options: "Whole repo" / "Specific folder or module". Do NOT list directories in this step. This question decides the scoping axis only. If AskUser is not available, default to whole repo.

  3. Second AskUser (conditional). Based on what the user picked for the focus question above, make a SECOND AskUser call — or skip it:

    • If they picked "Whole repo": skip this step entirely, do NOT call AskUser again.
    • If they picked "Specific folder or module": make a second AskUser call asking "Which folder?" with the discovered top-level directories as options.
  4. Quick scan. If scoped to a folder, focus LS/Grep/Read within that directory. Use LS, Glob, Grep, Read, and Execute to check for: missing/useless README, absent type annotations, cryptic variable names, missing tests, magic numbers, undocumented env vars, tangled imports, no inline comments. Spend a few tool calls gathering real observations.

  5. Generate the assessment. Write 1-2 short paragraphs (separated by a newline if two). Keep it concise, shorter is better. Don't pad with filler. Plain text, no emojis. describing the codebase's "Agent Fortress" status, what makes it impossible (or easy) for AI agents to understand. Reference specific real findings.

Style

Write like a human, not a chatbot. No em dashes, no double dashes, no "it's worth noting", no "let's dive in", no "I'd be happy to", no bullet-point-as-personality. Dry bureaucratic assessment, like a government inspector filing a report on structural deficiencies. The tone is clinical and unsympathetic. Findings are stated as facts, not punchlines.

Read the full file on GitHub · 80 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. 5d ago First seen · 80 lines · 17 tokens per session scan A d02dd0636453

Subscribe to this mod's changes

agent-repellent is a skill published in the GitHub repository Factory-AI/cursed-plugins (105 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 934 once invoked, about $0.0001 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 2026-08-30.

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