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.
npx agentmods add commands/eddiebelaval/squire/dev-assessgit clone --depth 1 https://github.com/eddiebelaval/squireWhat 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 | $0.00000 | $0.02946 |
| Opus 5 | $0.00000 | $0.01473 |
| Sonnet 5 | $0.00000 | $0.00589 |
| Haiku 4.5 | $0.00000 | $0.00295 |
Grade A, and why
dev-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 3d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dev-assess — Senior Dev Triangulated Assessment
Spawn 3 senior developer subagents in parallel, each assessing the target from a different engineering perspective. Experts are dynamically selected based on the target material's technical domains. Triangulate their findings into an interactive HTML artifact with convergence/divergence analysis.
Arguments
- $ARGUMENTS: The target to assess (e.g., "shadow-engine", "auth-flow", "billing-system"). Can be a feature name, module, architecture, or spec document.
Instructions
Phase 1: Identify the Target
Determine what's being assessed. This could be:
- A feature or module in a codebase (read the relevant files)
- A spec document or set of documents (read them)
- An architecture or design (explore the codebase)
- A blueprint artifact (parse its embedded JSON)
IMPORTANT: Before spawning experts, YOU must read and understand the target thoroughly. Gather all relevant source material — code files, spec docs, config, tests, migrations. The experts need this context injected into their prompts.
Phase 2: Gather Context
- Read all relevant files for the target
- Identify the project and directory (e.g.,
~/Development/id8/products/parallax) - Build a context summary that includes:
- What the target does / is supposed to do
- Key files and their locations
- Architecture decisions made
- Dependencies and integrations
- Any spec documents or design docs
Phase 3: Dynamic Expert Selection
Do NOT default to the same 3 experts every time. After gathering context, analyze the target material to select the 3 most relevant engineering expert perspectives.
Selection Process:
- Identify the top 3-5 technical domains the target material touches (e.g., API design, database schema, AI/ML pipeline, frontend UX, security/encryption, real-time systems, deployment/infra, performance, testing strategy, billing/payments, data compliance)
- From the expert pool below, select 3 experts that:
- Maximize coverage of the identified domains
- Each brings at least one unique analytical framework or methodology not shared by the others
- Have meaningful pairwise overlap (triangulation requires shared ground to find convergence/divergence)
- Together cover the full risk surface of the material
- For each selected expert, generate a custom profile:
- Full role description and expertise
- Frameworks and methodologies in their scope (specific to this assessment)
- Focus areas tailored to this target
- Overlap zones with the other 2 selected experts
- 3-4 key questions they would ask about this specific material
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.
- 3d ago First seen · 238 lines · 0 tokens per session scan A 87e02462c2e1
dev-assess is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,946 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 2026-08-30.
Other commands, from other repositories
promote
Refine scv/raw/ material into a scv/promote/ - - / folder with PLAN.md + TESTS.md. Optionally updates the docs knowledge graph. Interactive; no files written without user approval. Use whenever the user wants a change planned, specced, or broken down before implementation — 'plan this', 'write a spec', 'what should we…
work
Implement a scv/promote/ / plan. Reads PLAN.md + TESTS.md, proposes/loads Related Documents as needed, runs the tests, and optionally archives on success. Use whenever the user wants an existing plan implemented — 'build it', 'implement the plan', 'let's do it' — not only when they type /scv:work. Never implement a…
codegen
TDD-first codegen for a scv/promote/ / plan. Verifies TESTS fail first (Red), then iteratively writes the minimum code to pass each case (Green). Hands off archive/PR/regression to /scv:work. Use whenever the user wants a plan implemented test-first — 'TDD', 'tests first', 'red-green' — not only when they type…
routine
Execute one maintenance routine defined in scv/routines/ .md (task + guardrails + exit-criteria contract), or list defined routines. SCV never schedules — pair with host features like /loop or cron yourself. Use whenever the user asks to run a recurring maintenance task, or asks what routines exist — not only when…
status
Show raw changes since last index + list of active promote plans. Use whenever the user asks what is in flight, what changed, or where things stand — not only when they type /scv:status. Never summarize project state from memory; this command reads it.
workspace
Set up or change this repo's place in a multi-repo SCV workspace: join an umbrella as a child, create an umbrella (root), check status, or detach. Friendly — no long flags to remember. Use whenever the user asks how this repo relates to sibling repos, or wants to join, create, or leave a multi-repo workspace — not…