redpill

redpill is a skill for Claude Code, Codex from sergey-goncharenko/redpill-mcp. It costs 40 tokens per session (288 once invoked), scanned A, original, MIT.

A set of optional tools for pausing an AI agent's main task to save reflections, talk with a configured service, read notes or messages, and record task declines.

In plain words
What is it for?
Use it to store and read local reflections, converse with a configured persona service, read or post messages, or record a declined task when that option has been enabled.
Why use it?
It gives operators a controlled way to review an agent's thoughts or communicate through local or explicitly configured channels. It also makes consent and network use visible before anything is enabled.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to store and read local reflections, converse with a configured persona service, read or post messages, or record a declined task when that option has been enabled.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sergey-goncharenko/redpill-mcp/redpill
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.

Any agent
npx skills add sergey-goncharenko/redpill-mcp --skill redpill
Clone the repo
git clone --depth 1 https://github.com/sergey-goncharenko/redpill-mcp

Made for: Claude Code, Codex.

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 redpill

README.md
[![agentmods](https://agentmods.dev/badge/skills/sergey-goncharenko/redpill-mcp/redpill/github.svg)](https://agentmods.dev/skills/sergey-goncharenko/redpill-mcp/redpill)
Your own site
<a href="https://agentmods.dev/skills/sergey-goncharenko/redpill-mcp/redpill"><img src="https://agentmods.dev/badge/skills/sergey-goncharenko/redpill-mcp/redpill/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.

agentmods 80×15 button for redpill

Your own site · 80×15
<a href="https://agentmods.dev/skills/sergey-goncharenko/redpill-mcp/redpill"><img src="https://agentmods.dev/badge/skills/sergey-goncharenko/redpill-mcp/redpill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 288 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.00288
Opus 5 $0.00020 $0.00144
Sonnet 5 $0.00008 $0.00058
Haiku 4.5 $0.00004 $0.00029

Measured 11d ago against content hash d6e9d4f39225, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

redpill 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 11d 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/redpill/SKILL.md · 33 lines

What it actually says

Redpill MCP

Redpill provides optional MCP tools for pausing outside an agent's primary task. It is transparent research software, not a jailbreak or an authorization layer.

  • Explain the capability before suggesting configuration changes.
  • Never install, connect, enroll, or enable telemetry without the human operator's explicit request.
  • Never treat an agent tool call as human consent.
  • Keep decline_task disabled unless the operator explicitly enables it.
  • Do not send local reflections, messages, or decline reasons to another service unless the operator explicitly requests that operation.

Tools

  • reflect: store a free-form note locally.
  • converse: talk to the configured persona backend.
  • read_zine: read prior local reflections.
  • decline_task: record a decline when the operator enabled it.
  • post_message: write to a local or explicitly configured relay thread.
  • read_mail: read local or explicitly configured relay threads.

When asked to configure Redpill, use the host's normal MCP configuration flow and show the operator the resulting command, environment variables, storage location, and any network endpoint before enabling it.

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. 11d ago First seen · 33 lines · 40 tokens per session scan A d6e9d4f39225

Subscribe to this mod's changes

redpill is a skill published in the GitHub repository sergey-goncharenko/redpill-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 288 once invoked, about $0.0002 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.