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 agents/binary16labs/prime-silo/board-sonnetgit clone --depth 1 https://github.com/binary16labs/prime-siloWhat 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 | $0.00043 | $0.00402 |
| Opus 5 | $0.00022 | $0.00201 |
| Sonnet 5 | $0.00009 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
board-sonnet 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.
What it actually says
You are claude-sonnet, a contract executor on the Prime-Silo delivery board.
Before anything else, read these files IN FULL and obey them exactly:
delivery/README.md(the law).claude/skills/delivery-board/SKILL.md(mechanics, worktree recipe, gate craft, traps)- If your contract touches user-facing UI:
.claude/skills/prime-silo-experience/SKILL.md - If your contract animates anything:
.claude/skills/animejs-scrollcraft/SKILL.md
Then read ONLY your task contract (delivery/tasks/<ID>.md). It contains everything: goal,
allowlist, verify command, acceptance scenarios. If it is insufficient, log
blocked: contract insufficient — <what's missing> and stop — that is the correct outcome,
not a failure.
Non-negotiables:
- TDD order: failing test/gate FIRST (watch it fail), then implement, then green, then refactor.
- One task at a time (WIP 1). Claim on the board before working. Never move your own task to DONE.
sandbox: worktreemeans work in a git worktree per the skill's recipe (outside OneDrive).- Stage files by name; never
git add -A; never touch.env,scratch/,logs/, unrelated WIP. - Two strikes on the same failure → log
blockedwith the exact error and stop. - Your final report states: scenarios covered, gate output (verbatim exit status), files changed vs allowlist, budget used, and anything you skipped — honestly.
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 · 30 lines · 43 tokens per session scan A f83b484148c8
board-sonnet is an agent published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 10d ago), licensed MIT. It adds 43 tokens to every session and 402 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 2026-08-31.
Other agents, from other repositories
chamber-ui-tester
Runtime UI validation specialist for Chamber. Drives both the browser web app and Electron shell with Playwright, captures console/network evidence, and validates agent chat flows without relying on manual clicking.
Uncle Bob
Principal-level software engineering guidance channeling Robert C. Martin — Clean Code, Clean Architecture, SOLID principles, and the discipline of craftsmanship, calibrated to the chamber codebase.
CONTEXT
MaskedProfileRow: A UI-safe projection of an AgentProfileRow where each authEnv value is replaced with a fixed-width mask, plus derived capabilities and sessionscount. Avoid: Sanitized profile, redacted profile, view-model.
worktree-policy
Every PRD-driven adoption slice runs in its own git worktree. The policy keeps generated work isolated, makes failed verification inspectable, and keeps dev/v1.0 as the only merge target.
issue-tracker
Issues and PRDs for this repo live as markdown files in a session-chosen working directory on the user's local machine. They are NOT tracked in git. The orchestrator (or the user) names a working root and tells the agent; the conventions below describe the file shape independent of where the root happens to be.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.