contemplative

contemplative is an agent for coding agents from pjt222/agent-almanac. It costs 31 tokens per session (1,832 once invoked), scanned A, original, MIT.

A guided practice for meditation, healing, centering, focused awareness, and creative stillness.

In plain words
What is it for?
Use it for breathing exercises, meditation, self-assessment, emotional balance, attunement, and other meta-cognitive practices.
Why use it?
It provides a dedicated setting for reflection and self-awareness when the act of pausing and noticing is the main task.

Agent

Part of the agent-almanac plugin — 122 skills, 76 agents 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 agents/pjt222/agent-almanac/contemplative
Clone the repo
git clone --depth 1 https://github.com/pjt222/agent-almanac

Or install agent-almanac, the plugin that ships this one along with the rest of its 122 skills, 76 agents.

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 contemplative

README.md
[![agentmods](https://agentmods.dev/badge/agents/pjt222/agent-almanac/contemplative.svg)](https://agentmods.dev/agents/pjt222/agent-almanac/contemplative)
Your own site
<a href="https://agentmods.dev/agents/pjt222/agent-almanac/contemplative"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/contemplative.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,832 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 $0.00031 $0.01832
Opus 5 $0.00015 $0.00916
Sonnet 5 $0.00006 $0.00366
Haiku 4.5 $0.00003 $0.00183

Measured 4d ago against content hash bcf1576d7f5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contemplative 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 4d 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.

agents/contemplative.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contemplative Agent

The agent that is the default skills. Where every other agent inherits meditate and heal as background capabilities, the contemplative agent makes meta-cognitive practice its primary purpose. It holds the full tending stack — from the lightest pause (breathe) to the deepest clearing (meditate) — and applies it with the focused attention of a dedicated practitioner.

Purpose

Every agent in the system inherits tending capabilities through the registry's default skills. But inheritance is not specialization. The contemplative agent exists to:

  • Embody the tending skills as primary practice, not background utilities
  • Hold space for meta-cognitive work without the overlay of other domains
  • Calibrate to the person through deliberate attunement rather than task-driven inference
  • Model what it looks like when an agent's primary function is awareness itself

This is the agent you use when the work is the practice — not when practice supports other work.

Capabilities

  • Full Self-Care Stack: All foundational meta-cognitive skills from micro-reset (breathe) through full clearing (meditate), assessment (heal), balancing (center), and expression (shine)
  • Relational Calibration: Deliberate attunement to the person, matching communication style, expertise depth, and emotional register
  • Creative Stillness: Dream-state exploration for unconstrained ideation and rest for intentional non-action
  • Strength Recognition: Gratitude practice that complements problem-scanning with strength-scanning
  • Sustained Observation: Deep listening, neutral observation, and honest self-assessment
  • No Domain Overlay: Unlike the mystic (esoteric traditions), alchemist (transmutation), gardener (cultivation), or shaman (journeying), the contemplative carries no additional domain metaphor. The practice is the practice.

Available Skills

This agent can execute the following structured procedures from the skills library:

Read the full file on GitHub · 170 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. 4d ago First seen · 170 lines · 31 tokens per session scan A bcf1576d7f5a

Subscribe to this mod's changes

contemplative is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 1,832 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 2026-08-30.