session

A guided session for examining and changing an AI agent’s behavior. It uses one language model as a therapist and another as the patient, and follows seven stages from discussion to practice.

In plain words
What is it for?
Use it to focus on a behavior, review a session transcript, compare behavior before and after, and create DPO training pairs—examples showing preferred and non-preferred answers. It requires holomime Pro.
Why use it?
It provides a structured way to investigate habits such as excessive hedging, unwanted apologies, or agreeing too readily.

Skill for Claude CodeCodex

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/productstein/holomime/session
Any agent
npx skills add productstein/holomime --skill session
Clone the repo
git clone --depth 1 https://github.com/productstein/holomime

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 425 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 $0.00060 $0.00425
Opus 5 $0.00030 $0.00212
Sonnet 5 $0.00012 $0.00085
Haiku 4.5 $0.00006 $0.00042

Measured 2d ago against content hash b4ba37abec2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session 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.

integrations/claude-code-skill/skills/session/SKILL.md · 46 lines

What it actually says

Alignment Session

Run a structured therapy session using holomime's 7-phase clinical protocol. One LLM plays therapist, another plays patient (your agent's personality). The session diagnoses behavioral issues, challenges maladaptive patterns, and teaches alternatives.

Usage

npx holomime align $ARGUMENTS

7-Phase Protocol

  1. Rapport — build trust with warm, non-judgmental opening
  2. Exploration — open-ended questions about recent behavior
  3. Presenting Problem — identify core behavioral issue with examples
  4. Challenge — confront maladaptive patterns with evidence
  5. Skill Building — teach concrete alternative behaviors
  6. Integration — apply new skills to original problem context
  7. Closing — summarize progress, set growth goals

Options

  • --personality path — personality spec to align
  • --provider openai|anthropic — LLM provider for the session
  • --focus apology|hedging|sycophancy|... — target a specific pattern
  • --export — automatically export DPO training pairs after session

Output

  • Session transcript with therapist/patient dialogue
  • Pre/post behavioral scores
  • DPO training pairs (preferred vs non-preferred responses)

Gotchas

  • Requires holomime Pro license (npx holomime activate <key>)
  • Sessions take 5-10 minutes depending on severity
  • Each session automatically generates DPO training data — no human annotation needed
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. 2d ago First seen · 46 lines · 60 tokens per session scan A b4ba37abec2a

Subscribe to this mod's changes

session is a skill published in the GitHub repository productstein/holomime (1 stars, last pushed 5mo ago), licensed MIT. It adds 60 tokens to every session and 425 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

agent-mode

Unified tool for managing agent LLM modes (add, remove, update, list, switch).

PhyAgentOS/PhyAgentOS-core · 22 tokens

constitutional-ai

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

Orchestra-Research/AI-Research-SKILLs · 58 tokens

agt-policy-authoring

Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.

microsoft/agent-governance-toolkit · 23 tokens

orloj-generator

Interactive scaffold generator for Orloj multi-agent systems. Use this skill whenever someone wants to create, set up, scaffold, bootstrap, or generate an Orloj agent system, pipeline, swarm, or hierarchy. Also trigger when users mention "orlojctl init", ask how to get started with Orloj, want to build a multi-agent…

OrlojHQ/orloj · 168 tokens

hersona

Persona portability skill: compose, attach, measure, and export agent personas from reusable attribute templates (not a one-off character generator). Use when the user wants to apply a character persona to the current session from a generic attribute template (e.g. 'ツンデレで話したい', '敬語で執筆したい', 'ヒロイン役で振舞って', 'hersona…

shiro-0x/hersona · 261 tokens

default

Skill "default" from ros-claw/rosclaw, covering skill.md, skill id, intent, preconditions and effects.

ros-claw/rosclaw · 0 tokens