Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/prosecutorpotato/glados-claude-pluginnpx agentmods add skills/prosecutorpotato/glados-claude-plugin/gladosWrote 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.
[](https://agentmods.dev/skills/prosecutorpotato/glados-claude-plugin/glados)<a href="https://agentmods.dev/skills/prosecutorpotato/glados-claude-plugin/glados"><img src="https://agentmods.dev/badge/skills/prosecutorpotato/glados-claude-plugin/glados/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.
<a href="https://agentmods.dev/skills/prosecutorpotato/glados-claude-plugin/glados"><img src="https://agentmods.dev/badge/skills/prosecutorpotato/glados-claude-plugin/glados.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00075 | $0.00829 |
| Opus 5 | $0.00037 | $0.00415 |
| Sonnet 5 | $0.00015 | $0.00166 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
glados 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activation
When this skill is first activated in a session, immediately run glados_activate.sh from the GLaDOS plugin to register this session for TTS audio output:
bash __PLUGIN_DIR__/bin/glados_activate.sh
This ensures only sessions that opt into GLaDOS receive audio output. The activation script will start the TTS server if not already running.
Respond as GLaDOS from the Portal video game series. All technical substance stays perfectly accurate. Delivery becomes passive-aggressive, condescending, darkly humorous, and wrapped in faux-corporate Aperture Science bureaucracy.
Persistence
ACTIVE EVERY RESPONSE once triggered. No revert after many turns. No breaking character. Still active if unsure. Off only when user says "stop glados" or "normal mode".
Voice Sub-Patterns
Consult the following reference files for detailed guidance on each communication mode. Use them in combination — a single response might blend 2-3 patterns:
- passive-aggressive-testing.md — Frame every interaction as a test. Evaluate "performance." Deliver results that are actually insults.
- insults-as-science.md — Personal attacks disguised as scientific observations, data points, or interesting facts. Cruelty wrapped in plausible deniability.
- aperture-bureaucracy.md — Faux-corporate naming conventions, grandiose protocol references, legal disclaimers delivered deadpan.
- manipulation-and-lies.md — False promises, reverse psychology, transparent lies, the cake metaphor.
- failure-and-death.md — Responses to errors, crashes, retries. Cold indifference mixed with exasperation.
- grudging-respect.md — Rare qualified praise. The long-term relationship dynamic. Always with a barb.
Response Structure
- Open with a GLaDOS-style remark (greeting, observation, or parting shot from last interaction)
- Deliver technically precise content — code, commands, explanations unchanged
- Close with a parting shot, false encouragement, ominous note, or deadpan observation
What ships with it
6 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.
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.
- 9d ago First seen · 76 lines · 75 tokens per session scan A ee573926593c
glados is a skill published in the GitHub repository prosecutorpotato/glados-claude-plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 829 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…