delivery-board

delivery-board is a skill for Claude Code from binary16labs/prime-silo. It costs 68 tokens per session (2,080 once invoked), scanned A, original, MIT.

A workflow guide for managing tasks on a delivery board, the project’s shared list of work and its status.

In plain words
What is it for?
Taking the next ready task, creating a failing test first, working within the task’s allowed files, running its verification gate, and handing completed work to an independent verifier.
Why use it?
It defines how to select, claim, implement, test, verify, and log work so multiple agents can coordinate without losing track of ownership or review.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

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 skills/binary16labs/prime-silo/delivery-board
Any agent
npx skills add binary16labs/prime-silo --skill delivery-board
Clone the repo
git clone --depth 1 https://github.com/binary16labs/prime-silo

Made for: Claude Code.

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.

agentmods badge for delivery-board

README.md
[![agentmods](https://agentmods.dev/badge/skills/binary16labs/prime-silo/delivery-board.svg)](https://agentmods.dev/skills/binary16labs/prime-silo/delivery-board)
Your own site
<a href="https://agentmods.dev/skills/binary16labs/prime-silo/delivery-board"><img src="https://agentmods.dev/badge/skills/binary16labs/prime-silo/delivery-board.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,080 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00068 $0.02080
Opus 5 $0.00034 $0.01040
Sonnet 5 $0.00014 $0.00416
Haiku 4.5 $0.00007 $0.00208

Measured 6d ago against content hash 79f4faebc63a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

delivery-board scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Zero-dep Node ESM (`node:fs`, `node:path`, `node:child_process` only). Exit 0 = pass,
.claude/skills/delivery-board/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delivery-board operator — run the board without supervision

The board at delivery/board/BOARD.md is the single source of work. delivery/README.md is the law — read it once per session, follow it exactly. This skill adds what README assumes you know: the mechanics, the tier routing, and the traps that have actually burned agents in this repo.

1. The loop (memorize this shape)

read README → read BOARD → take TOPMOST READY item → claim (board edit + LOG line + commit)
→ read ONLY your contract (delivery/tasks/<ID>.md) → make a worktree if sandbox: worktree
→ TDD: failing test/gate FIRST, watch it fail → implement inside the allowlist → gate green
→ move board line to VERIFY + LOG `ready-for-verify` + commit → STOP (never self-DONE)
  • Claim commit message: chore(delivery): claim <ID> · work commits: feat(<ID>): <what> / test(<ID>): <scenario name> · verify handoff: chore(delivery): <ID> ready-for-verify.
  • LOG format (append-only, never edit): <ISO-ts> | <ID> | <event> | <agent> | <note> Events: claimed, ready-for-verify, verified-by, blocked, unblocked, note.
  • Agent identity: use <harness>-<tier> (e.g. claude-sonnet, claude-haiku-verifier).
  • Promotion rule: when the last dep of an AUTHORED item is verified DONE, move it to the BOTTOM of READY with a note (dep <X> DONE — entered READY <date>). Anyone may promote; only the human reorders READY.
  • Two strikes → blocked. Same failure twice: log blocked with the exact error and what you tried. Do not redesign around the contract. Do not brute-force a third attempt.

2. Model-tier routing (who takes what)

Tier Takes Never takes
haiku Independent VERIFICATION of others' tasks (re-run gate from clean checkout, tick BDD scenarios, move VERIFY→DONE), mechanical single-surface contracts (grep-and-replace passes like C4 execution, LOG/board hygiene, running gates) Contract authoring, anything with design judgment, multi-file architecture, writing new gates
sonnet Standard contracts: layout/CSS work (C1), SSE/API endpoints (B1), keyframe+binding work (C5), test suites, gate scripts from a spec, docs passes Contract authoring/splitting, taste-defining UI (first impressions), cross-workstream tradeoffs
opus Design-taste flagships (C3 login/first-run, D1 Studio spec, E-workstream visual), contract authoring/splitting at plan checkpoints, anything touching >2 workstreams, unblocking a task two tiers failed Bulk mechanical work (wasteful)

Read the full file on GitHub · 116 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. 6d ago First seen · 116 lines · 68 tokens per session scan A 79f4faebc63a

Subscribe to this mod's changes

delivery-board is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 2,080 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.