agentmods.dev

hatchet-mcp: Skill for Claude Code

.claude/skills/new-spec/SKILL.md

new-spec is a skill for Claude Code from DanMeon/hatchet-mcp. It costs 81 tokens per session (1,717 once invoked), scanned A, original, MIT.

A skill for starting a new version specification and its paired architecture decision record, or ADR—a document that records important design reasoning. It also adds the specification to the project's index.

In plain words
What is it for?
Use it when beginning a new versioned feature or phase, such as a v0.2.0 change, with a topic written in kebab-case.
Why use it?
It creates the required planning documents in the expected locations and stops if a specification with the same name already exists.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

This is DanMeon/hatchet-mcp's own configuration. It tells Claude Code how to work on hatchet-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hatchet-mcp configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is | <version> (<topic>) | Draft | [<version>/<topic>.md](<version>/<topic>.md) | [design/<version>/<topic>-research.md](../design/<version>/<topic>-research.md) |.

not rated 0repo 2mo ago A scan 81 tokens original MIT
View source ↗ DanMeon/hatchet-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to DanMeon/hatchet-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DanMeon/hatchet-mcp/main/.claude/skills/new-spec/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/DanMeon/hatchet-mcp

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 new-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/danmeon/hatchet-mcp/new-spec/github.svg)](https://agentmods.dev/skills/danmeon/hatchet-mcp/new-spec)
Your own site
<a href="https://agentmods.dev/skills/danmeon/hatchet-mcp/new-spec"><img src="https://agentmods.dev/badge/skills/danmeon/hatchet-mcp/new-spec/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.

agentmods 80×15 button for new-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/danmeon/hatchet-mcp/new-spec"><img src="https://agentmods.dev/badge/skills/danmeon/hatchet-mcp/new-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00081 $0.01717
Opus 5 $0.00041 $0.00859
Sonnet 5 $0.00016 $0.00343
Haiku 4.5 $0.00008 $0.00172

Measured 9d ago against content hash 1b3d1515dfc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

new-spec 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 9d 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.

.claude/skills/new-spec/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/new-spec — scaffold a new version spec

Given <version> (e.g. v0.2.0) and <topic> (e.g. mutating-tool-gate), create a new per-version spec, its paired ADR (design research), and the index entry in one shot.

Outputs

  1. docs/roadmap/<version>/<topic>.md — the spec body (frontmatter status: Draft, version: <version>)
  2. docs/design/<version>/<topic>-research.md — the paired ADR (same frontmatter)
  3. docs/roadmap/README.md — append a row to the active spec index table

Procedure

When this skill is invoked, execute the following steps in order:

  1. Validate arguments

    • version must match the SemVer pattern vX.Y.Z
    • topic must be kebab-case ([a-z0-9]+(-[a-z0-9]+)*)
    • Abort if docs/roadmap/<version>/<topic>.md already exists — never overwrite an existing spec

  2. Read the four files which are the SSOT for body structure:

    • templates/spec.md — spec body skeleton (placeholders only, copied directly)
    • templates/adr.md — ADR skeleton (placeholders only, copied directly)
    • references/spec.md — per-section rules for the spec body (single-phrase title, intro = core summary without scattered detail, behavior-driven AC-N, etc.)
    • references/adr.md — per-section rules for the ADR (standard intro phrase, four subsections (### Facts / ### Validator Counter-Arguments / ### Final Decision / ### Primary Sources))

    Also re-read docs/CONVENTIONS.md for cross-cutting policy: § Status Metadata (frontmatter schema), § Section Role Separation (info routing lookup), § Cross-Link Direction Rules, § Naming Rules, § Acceptance Criteria Format. Conventions are Living and may have evolved since the last skill invocation.

  3. Create directories if missing:

    • docs/roadmap/<version>/
    • docs/design/<version>/

  4. Write docs/roadmap/<version>/<topic>.md by copying templates/spec.md verbatim and substituting placeholders (<version> / <topic> / <topic phrase> / intro prose / Decisions table entries / AC bullets / Non-Goals bullets). Apply the references/spec.md per-section rules — especially the intro rule (no detail, defer to Decisions table cells), which is the most-violated rule.

Read the full file on GitHub · 78 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 78 lines · 81 tokens per session scan A 1b3d1515dfc5

Subscribe to this mod's changes

new-spec is a skill published in the GitHub repository DanMeon/hatchet-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 1,717 once invoked, about $0.0004 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.

OrchestrationPlanningWriting and docshatchethatchet-sdkmcpmodel-context-protocol
Related

Other skills, from other repositories

multi-agent-workflow

Planner → workers → critic loop for SuperAgenticMCP missions. Use when coordinating multi-step agent work across racked MCP servers.

ANAMIZED/SuperAgenticMCP · 32 tokens

Subagent Driven Development

Orchestrate specialized, autonomous AI agents to execute parallel subtasks with strict boundaries.

ankur-gaurav161418/omniforge · 22 tokens

multi-agent-workflow

Orchestrate sequential multi-agent workflows under a shared budget on OpenMesha. Use when a goal needs planner/researcher/worker roles or council-style decomposition.

ANAMIZED/OpenMesha · 38 tokens

multi-agent-workflow

Create and run multi-agent workflows on Server OS.

ANAMIZED/Server-OS · 15 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

atmos-auth

Authentication and identity management: providers (SSO/SAML/OIDC/GCP/Atmos Pro), identities, keyring, identity chaining, login/exec/shell/console, and github/sts for private GitHub access.

cloudposse/atmos · 48 tokens