Borrowing it
Nothing to install: this file belongs to binary16labs/prime-silo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/binary16labs/prime-silo/main/.claude/skills/delivery-board/SKILL.mdgit clone --depth 1 https://github.com/binary16labs/prime-siloWrote 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/skills/binary16labs/prime-silo/delivery-board)<a href="https://agentmods.dev/skills/binary16labs/prime-silo/delivery-board"><img src="https://agentmods.dev/badge/skills/binary16labs/prime-silo/delivery-board/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/skills/binary16labs/prime-silo/delivery-board"><img src="https://agentmods.dev/badge/skills/binary16labs/prime-silo/delivery-board.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 55 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Prompt Injection · line 34 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 34 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 37 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Agent Snooping · line 95 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 96 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00068 | $0.02080 |
| Opus 5.5 | $0.00027 | $0.00832 |
| Sonnet 5.5 | $0.00014 | $0.00416 |
| Haiku 4.5 | $0.00007 | $0.00208 |
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 2mo 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, 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
blockedwith 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) |
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.
- 2mo ago First seen · 116 lines · 68 tokens per session scan A 79f4faebc63a
delivery-board is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 13d ago), licensed MIT. It adds 68 tokens to every session and 2,080 once invoked, about $0.0003 per session on Opus 5.5. 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.
delivery-board compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| delivery-boardbinary16labs/prime-silo | Skill | 5 | 13d ago | MIT | A | 68 | Claude Code |
| dcp-citizenshipdcp-ai-protocol/dcp-ai | Skill | 23 | yesterday | Apache-2.0 | A | 22 | Claude Code, Codex |
| compose:worktreesergezuber/FABULA-LLM-5 | Skill | 82 | 1mo ago | MIT | A | 35 | Claude Code, Codex |
| compose:mergesergezuber/FABULA-LLM-5 | Skill | 82 | 1mo ago | MIT | A | 41 | Claude Code, Codex |
| compose:new-skillsergezuber/FABULA-LLM-5 | Skill | 82 | 1mo ago | MIT | A | 21 | Claude Code, Codex |
| compose:reportsergezuber/FABULA-LLM-5 | Skill | 82 | 1mo ago | MIT | A | 33 | Claude Code, Codex |
| ironmesh-sendWizTheAgent/IronMesh | Skill | 26 | 11d ago | MIT | A | 49 | Claude Code |