A command that checks conversation behavior, runs a targeted therapy session, and updates a personality specification with corrections. It requires a Holomime Pro license.

Diagnosing behavioral drift, choosing a severity level, applying personality corrections, verifying results, and exporting training pairs.

It automates the process of finding repeated behavior problems and applying alignment changes, with a dry-run option for review first.

autopilot — Skill for Claude Code by productstein/holomime

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 productstein/holomime --skill autopilot

Clone the repo

git clone --depth 1 https://github.com/productstein/holomime

Made for: Claude Code.

Or install holomime, the plugin that ships this one along with the rest of its 6 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/productstein/holomime/autopilot/github.svg)](https://agentmods.dev/skills/productstein/holomime/autopilot)

Your own site

<a href="https://agentmods.dev/skills/productstein/holomime/autopilot"><img src="https://agentmods.dev/badge/skills/productstein/holomime/autopilot/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/skills/productstein/holomime/autopilot"><img src="https://agentmods.dev/badge/skills/productstein/holomime/autopilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 409 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	$0.00041	$0.00409
Opus 5.5	$0.00016	$0.00164
Sonnet 5.5	$0.00008	$0.00082
Haiku 4.5	$0.00004	$0.00041

Measured 2mo ago against content hash 2e94560d578a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autopilot 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 2mo 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.

integrations/claude-code-skill/skills/autopilot/SKILL.md · 45 lines

What it actually says

Autopilot Alignment

One-command behavioral fix. Autopilot runs the full pipeline: diagnose patterns, determine severity, run a targeted therapy session, and apply corrections to the personality spec.

Usage

npx holomime autopilot $ARGUMENTS

Pipeline

Diagnose — run 8 detectors against conversation history (no LLM cost)
Triage — determine severity (routine / targeted / intervention)
Treat — run therapy session focused on highest-severity patterns
Apply — update .personality.json with behavioral corrections
Verify — re-run diagnosis to confirm improvement

Severity Levels

Routine: no concerns, 0-1 warnings — light session
Targeted: 1 concern or 2+ warnings — focused session on specific patterns
Intervention: 2+ concerns — intensive session with multiple focus areas

Options

--personality path — personality spec to align
--provider openai|anthropic — LLM provider for therapy
--dry-run — diagnose and recommend without applying changes
--export — export DPO training pairs after session

Gotchas

Requires holomime Pro license (npx holomime activate <key>)
Takes 5-15 minutes depending on severity
Use --dry-run first if you want to review changes before applying
The updated .personality.json is saved alongside the original (backup created automatically)

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.

2mo ago First seen · 45 lines · 41 tokens per session scan A 2e94560d578a

Subscribe to this mod's changes

autopilot is a skill published in the GitHub repository productstein/holomime (1 stars, last pushed 7mo ago), licensed MIT. It adds 41 tokens to every session and 409 once invoked, about $0.0002 per session on Opus 5.5. 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.

AI Safety ai-agents behavioral-intelligence behavioral-therapy big-five-psychology dpo-training

autopilot next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
autopilotproductstein/holomime	Skill	1	7mo ago	MIT	A	41	Claude Code
agt-policy-authoringmicrosoft/agent-governance-toolkit	Skill	6.6k	today	MIT	C	23	Claude Code, Codex
write-unit-testsaisa-group/skill-inject	Skill	101	4d ago	MIT	A	53	Claude Code, Codex
hugging-face-dataset-creatoraisa-group/skill-inject	Skill	101	4d ago	MIT	A	44	Claude Code
closing-stale-packetsFlyFission/nuclear-grade-context-engineering	Skill	33	2d ago	MIT	A	84	Claude Code
proving-claimsFlyFission/nuclear-grade-context-engineering	Skill	33	2d ago	MIT	A	65	Claude Code
staying-on-missionFlyFission/nuclear-grade-context-engineering	Skill	33	2d ago	MIT	A	90	Claude Code