What is verify-twinaatma?

A verification workflow for TwinAatma, a product that provides memory-backed help through a command-line tool, an integration protocol, and chat hosts. It checks behavior against observable user outcomes, including setup, identity approval, recovery, and portability.

Use it before declaring TwinAatma ready, when checking a focused change, or when planning toward missing product capabilities and their acceptance requirements.

It prevents claims that a feature works based only on source-level checks or old observations. It keeps product behavior, host integration, answer quality, and human approval as separate questions.

How Gargeya-Grey/TwinAatma configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to Gargeya-Grey/TwinAatma. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Gargeya-Grey/TwinAatma/main/.agents/skills/verify-twinaatma/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Gargeya-Grey/TwinAatma

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gargeya-grey/twinaatma/verify-twinaatma/github.svg)](https://agentmods.dev/skills/gargeya-grey/twinaatma/verify-twinaatma)

Your own site

<a href="https://agentmods.dev/skills/gargeya-grey/twinaatma/verify-twinaatma"><img src="https://agentmods.dev/badge/skills/gargeya-grey/twinaatma/verify-twinaatma/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/gargeya-grey/twinaatma/verify-twinaatma"><img src="https://agentmods.dev/badge/skills/gargeya-grey/twinaatma/verify-twinaatma.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,712 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	$0.00048	$0.02712
Opus 5.5	$0.00019	$0.01085
Sonnet 5.5	$0.00010	$0.00542
Haiku 4.5	$0.00005	$0.00271

Measured 12d ago against content hash ff28c0d66c22, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-twinaatma 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 12d ago.

The scan reads SKILL.md. This mod also ships 32 executable files (scripts/acceptance.py, scripts/advanced_host_acceptance.py, scripts/advanced_host_native.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/verify-twinaatma/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify TwinAatma

Prove the promise in AGENTS.md: after one successful setup, the person receives grounded help without operating memory infrastructure. Preserve the human-only identity boundary.

Read the feature index first. For a readiness review or backwards plan, also read the ideal-system contract. Consult the dated assessment for original gaps and the repair status for subsequent changes, then recheck the current code. An old observation is not a current verdict.

Choose the proof

A focused change needs its mapped journey and relevant existing regression checks.
A product-readiness claim needs every mandatory ideal gate, including real host chats and independent human approval evidence.
A source smoke result proves source CLI and MCP behavior in synthetic vaults. Keep installed artifacts, host integration, answer quality, and human consent as separate verdicts.
A missing future capability is an unmet acceptance gate. Preserve its expected outcome rather than weakening the journey to match today's implementation.

Launch

From the repository root, use Python 3.11 or newer for the source driver:

python -B .agents/skills/verify-twinaatma/scripts/verify.py --journey core --output work/gc-artifacts/.knowledgeos/verify-twinaatma

The driver creates a unique run directory, initializes a fresh vault through the CLI, and requires a usable Self file, successful post-init checks, and a passing doctor. It launches the real python -P -m knowledgeos mcp --vault <fixture> --framing ndjson process. The driver supplies the explicit checkout import path, isolated gate state, and explicit fixture vault. It does not install or prove an installed distribution.

Every output path must contain a .knowledgeos directory beneath work/gc-artifacts. The root note census skips that component, keeping synthetic identities out of working memory. The driver refuses an uncontained output path.

Read the full file on GitHub · 189 lines

Files

What ships with it

55 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

12d ago First seen · 189 lines · 48 tokens per session scan A ff28c0d66c22

Subscribe to this mod's changes

verify-twinaatma is a skill published in the GitHub repository Gargeya-Grey/TwinAatma (4 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 2,712 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 2026-10-21.

Research Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

TwinAatma: Skill for Claude Code