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.
git clone --depth 1 https://github.com/eddiebelaval/squireWrote 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.
[](https://agentmods.dev/commands/eddiebelaval/squire/parallax-assess)<a href="https://agentmods.dev/commands/eddiebelaval/squire/parallax-assess"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/parallax-assess/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.
<a href="https://agentmods.dev/commands/eddiebelaval/squire/parallax-assess"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/parallax-assess.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.03831 |
| Opus 5 | $0.00000 | $0.01916 |
| Sonnet 5 | $0.00000 | $0.00766 |
| Haiku 4.5 | $0.00000 | $0.00383 |
Grade A, and why
parallax-assess 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/parallax-assess — Clinical Triangulated Assessment
Spawn 3 PhD-level clinical expert subagents in parallel, each assessing Ava's framework from a different therapeutic/ethical perspective. Experts are dynamically selected based on the target material's clinical domains. Triangulate their findings into an interactive HTML artifact with risk matrix, instrument coverage analysis, and adversarial scenario evaluation.
Arguments
- $ARGUMENTS: The target to assess (e.g., "shadow-engine", "interview-system", "safety-framework", "ava-voice"). Targets are always assessed in the context of Parallax/Ava's clinical framework.
Instructions
Phase 1: Identify the Target
Determine what's being assessed within Parallax's clinical framework. This could be:
- A new feature's psychological safety (e.g., Shadow Engine)
- An existing interaction pattern (e.g., interview system, solo mode)
- A safety mechanism (e.g., crisis detection, violence detection)
- A voice/tone specification (e.g., Ava's voice guide)
- An adversarial scenario playbook
IMPORTANT: Before spawning experts, YOU must read and understand the target thoroughly. Read all relevant spec documents, code files, safety configs, and prompt templates. The experts need full clinical context.
Phase 2: Gather Context
- Read all relevant files for the target within Parallax (
~/Development/id8/products/parallax) - Read any relevant spec documents (check iCloud
.docxfiles viatextutil -convert txt -stdout) - Read existing safety mechanisms:
src/lib/signal-detector.ts,src/ava/kernel/values.md,src/ava/models/ipv.md - Read the User Intelligence Layer research:
docs/research/user-intelligence-layer.md - Read the Shadow Engine specs if assessing shadow-related features
- Build a comprehensive clinical context summary including:
- What the target does in user-facing terms
- What psychological domains it touches
- What safety mechanisms exist
- What validated instruments are referenced
- What consent mechanisms are in place
- What the harm tiers look like
- Any adversarial scenarios documented
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.
- 6d ago First seen · 301 lines · 0 tokens per session scan A e31e2f0dbee1
parallax-assess is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,831 tokens. 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 2026-09-03.
Other commands, from other repositories
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
note
Zero-friction idea capture. Append, list, or promote notes to todos.
ralph-feedback
Parse raw feedback into structured format for review.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.