agentmods.dev

deckhand CLAUDE.md

deckhand CLAUDE.md is an instructions file for coding agents from jonthebeef/deckhand. It costs 765 tokens per session, scanned A, original, MIT.

Repository instructions for Deckhand, a Claude Code plugin containing tools for managing project backlogs and the lifecycle of tickets, which are tracked units of work.

In plain words
What is it for?
Use them to structure the plugin, update its shared version with the provided script, and prepare changes for release.
Why use it?
They keep the plugin's files, versions, releases, and platform support consistent as its tools change.

Instructions file

not rated 6 2mo ago A scan 765 tokens original MIT
View the source file jonthebeef/deckhand
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 instructions/jonthebeef/deckhand/claude-md
Clone the repo
git clone --depth 1 https://github.com/jonthebeef/deckhand

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 deckhand CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jonthebeef/deckhand/claude-md.svg)](https://agentmods.dev/instructions/jonthebeef/deckhand/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jonthebeef/deckhand/claude-md"><img src="https://agentmods.dev/badge/instructions/jonthebeef/deckhand/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 765 This file is loaded in full into every session.
When invoked 765 The same file — it is already loaded in full.
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 $0.00765 $0.00765
Opus 5 $0.00382 $0.00382
Sonnet 5 $0.00153 $0.00153
Haiku 4.5 $0.00076 $0.00076

Measured 3d ago against content hash 0b7e4d89645a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deckhand CLAUDE.md 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

A Claude Code **plugin** bundling two skills, `ticket-lifecycle` and `managing-project-backlog`. The same skills also run standalone on Codex and Cursor, so keep everything platform-agnostic (plain Markdown plus `gh` / `
CLAUDE.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

deckhand

A Claude Code plugin bundling two skills, ticket-lifecycle and managing-project-backlog. The same skills also run standalone on Codex and Cursor, so keep everything platform-agnostic (plain Markdown plus gh / curl, no Claude-Code-only hooks).

Layout

  • .claude-plugin/plugin.json - the plugin manifest (name, version, license, etc.). Only this file lives in .claude-plugin/.
  • skills/ticket-lifecycle/ and skills/managing-project-backlog/ - the two skills, each a SKILL.md plus supporting files. Skills live at skills/<name>/, not inside .claude-plugin/.
  • Root: VERSION, bump.sh, README.md, CHANGELOG.md, CLAUDE.md, LICENSE.

Versioning and releases

  • The version lives in four places, kept in sync: the root VERSION, skills/ticket-lifecycle/VERSION, skills/managing-project-backlog/VERSION, and the version field in .claude-plugin/plugin.json. They share a single number.
  • Do not edit those by hand. Use the helper: ./bump.sh patch | minor | major (or ./bump.sh X.Y.Z). It writes all four and prints the publish commands.
  • Bump whenever you ship a user-facing change to either skill: patch for fixes, minor for new behaviour, major for breaking changes. Add a CHANGELOG.md entry too.
  • A change is not "released" until the bump is on main. That triggers the standalone-skills update offer, and the plugin manager picks up the new plugin.json version. The check compares version strings, so the published number must only ever go up.

How updates reach users

  • Each skill's first-invocation protocol runs a throttled (once / 24h), opt-out version check and offers an update only when the local copy is behind. Stay-quiet-otherwise is the intended behaviour.
  • Updates are agent-driven and applied in place. They MUST preserve the user's populated board-config.md (it holds their real board IDs). If you ever touch the update or check instructions, keep that preservation rule intact and keep it working the same on Claude Code, Codex, and Cursor.

Read the full file on GitHub · 31 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. 3d ago First seen · 31 lines · 765 tokens per session scan A 0b7e4d89645a

Subscribe to this mod's changes

deckhand CLAUDE.md is an instructions file published in the GitHub repository jonthebeef/deckhand (6 stars, last pushed 2mo ago), licensed MIT. It adds 765 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Project managementagentic-workflowsai-agentsclaudeclaude-codedeveloper-tools
Related

Other instructions, from other repositories

nextclaw AGENTS.md

AGENTS.md instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.

Peiiii/nextclaw · 3,095 tokens

Commonly-used-high-value-skills AGENTS.md

AGENTS.md instructions for seaworld008/Commonly-used-high-value-skills, covering repository agent instructions, architecture overview, installation root by client, golden rules and automated operations (sop for ai agents).

seaworld008/Commonly-used-high-value-skills · 4,045 tokens

obsidian-knowledge-agent AGENTS.md

Instructions for Michael-OvO/obsidian-knowledge-agent, covering agents.md — obsidian knowledge agent, how to work, what this vault is, instruction files and core rules.

Michael-OvO/obsidian-knowledge-agent · 1,417 tokens

slipway AGENTS.md

Instructions for signalridge/slipway, covering slipway agent principles, user owns the process, investigate before clarifying, report, do not certify and maintain the whole surface.

signalridge/slipway · 470 tokens

nobrainer-tech-skills copilot-instructions.md

Instructions for nobrainer-tech/nobrainer-tech-skills: The fifteen canonical Agent Skills are under skills/; retired predecessors exist only in Git history. Read the relevant skills/ /SKILL.md before changing a skill.

nobrainer-tech/nobrainer-tech-skills · 359 tokens

agentic-rd-skill AGENTS.md

AGENTS.md instructions for TheStreamCode/agentic-rd-skill, covering repository instructions, purpose and sources of truth, repository invariants, implementation style and documentation synchronization.

TheStreamCode/agentic-rd-skill · 1,439 tokens