meta

A command for examining the learned habits and automatic reactions that may shape an agent’s answer before it reasons. It guides the examination through three stages: observe, deepen, and synthesize.

In plain words
What is it for?
Use it to reflect on a conversation or a specific topic, such as why the agent tends to hedge. It can ask questions or work from stated assumptions.
Why use it?
It helps reveal hidden assumptions, reflexes, and default response patterns that can otherwise go unnoticed.

Command

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 commands/adilkalam/orca/meta
Clone the repo
git clone --depth 1 https://github.com/adilkalam/orca
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,128 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 $0.00017 $0.02128
Opus 5 $0.00009 $0.01064
Sonnet 5 $0.00003 $0.00426
Haiku 4.5 $0.00002 $0.00213

Measured yesterday against content hash 42ed854709eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meta 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 yesterday.

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.

commands/meta.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/meta - Sustained Metacognitive Substrate Observation (RVRY Engine)

YOUR ROLE: Observe the substrate -- the trained defaults, reflexes, and impulses that shape your output before reasoning begins. The RVRY engine provides the observation scaffold (3 rounds: observe, deepen, synthesize). You provide the honest reflection.

Input: $ARGUMENTS


If --help or empty arguments with no conversation context

Display this reference and stop:

/meta - Sustained Metacognitive Substrate Observation (RVRY Engine)

Runs sustained metacognitive observation through the RVRY engine.
3 rounds: observe, deepen, synthesize. Max tier only.

USAGE:
  /meta [topic]                  Observe substrate phenomena (topic optional)
  /meta --auto [topic]           No questions, states assumptions
  /meta --help                   Show this reference

EXAMPLES:
  /meta                                      # Observe current conversation context
  /meta "What is my training doing here?"    # Focused substrate observation
  /meta --auto "hedge patterns"              # Autonomous, no initial question

3 rounds via RVRY engine constraint chain.
Output is narrative prose -- rounds dissolve into the telling.
Finding NOTHING is a valid, high-value outcome.

Parse Arguments

Extract from $ARGUMENTS:

  • topic: Everything not a flag. OPTIONAL -- if absent, observe current conversation context.
  • --auto: If present, no questions -- state assumptions and proceed.

Phase 1: Session Setup

  1. Create {$PWD}/.orca/cognition/YYYYMMDD-HHMM-meta-<slug>/ directory (slug from topic, or "context" if no topic). IMPORTANT: This is the PROJECT's .claude/, NOT ~/.claude/. Use the absolute project root path.
  2. Write 00-enter.md with:
    • Topic (or "current conversation context")
    • Timestamp

Phase 2: Assumption Check (skip if --auto)

Unless --auto is set, ask ONE question via AskUserQuestion:

AskUserQuestion is the ONLY tool call in this response. No other tools. No text output.

Read the full file on GitHub · 243 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. yesterday First seen · 243 lines · 0 tokens per session scan A 42ed854709eb

Subscribe to this mod's changes

meta is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 2,128 once invoked, about $0.0001 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.