umbel: Skill for Claude Code

.claude/skills/tend/SKILL.md

tend is a skill for Claude Code from jahala/umbel. It costs 55 tokens per session (2,616 once invoked), scanned A, original, MIT.

A project-planning guide that recommends the next action from the project's current state. It can also show progress and relationships between pieces of work.

In plain words
What is it for?
Use it when you need a next-step recommendation, a project status view, a feature plan, or a view of dependencies between features.
Why use it?
It reduces the guesswork involved in deciding what to work on next. It routes planning questions to the relevant project workflow.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is jahala/umbel's own configuration. It tells Claude Code how to work on umbel 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 umbel configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node dist/bin/tend.js next --json.

Reuse

Borrowing it

Nothing to install: this file belongs to jahala/umbel. 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/jahala/umbel/master/.claude/skills/tend/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jahala/umbel

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 tend

README.md
[![agentmods](https://agentmods.dev/badge/skills/jahala/umbel/tend.svg)](https://agentmods.dev/skills/jahala/umbel/tend)
Your own site
<a href="https://agentmods.dev/skills/jahala/umbel/tend"><img src="https://agentmods.dev/badge/skills/jahala/umbel/tend.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,616 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 $0.00055 $0.02616
Opus 5 $0.00028 $0.01308
Sonnet 5 $0.00011 $0.00523
Haiku 4.5 $0.00006 $0.00262

Measured 8d ago against content hash f2c8105e6552, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tend 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 8d 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/tend/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tend: Next-Action Router

Entry point for all tend-* skills. The primary move is route the user to their highest-leverage next step — computed deterministically by tend next from on-disk project state, with reasons drawn from the canonical reason-code vocabulary (src/core/reason-codes.ts). Status overviews and graph rendering are secondary.

What this skill assumes

  • The project has been initialized with tend init (garden polyglot at docs/tend/overview.html exists).
  • MCP tools are available — preferred path is mcp__tend__tend_get_next. CLI fallback is node dist/bin/tend.js next --json when MCP is not wired.
  • The user wants a routing recommendation, a status read, or to be handed off to a sub-skill.
  • Nothing is assumed about the project's spine state — if it's empty, the next-action engine returns a bootstrap action with reason code unbound_persona and this skill surfaces that as-is.

Trigger

  • "what should I do?" / "what's next?" / "what should I work on?" / "next action"
  • User mentions features, requirements, or planning
  • "show status", "what's the progress?"
  • "visualize", "show graph", "show dependencies"
  • Any /tend command without a more specific verb

Workflow

1. Compute the next action

Call the next-action engine. MCP path is preferred because it runs in-process and respects the same code the CLI does:

mcp__tend__tend_get_next       (preferred)

Fallback when MCP is not available:

node dist/bin/tend.js next --json

Both return the same NextAction shape:

{
  "action": "/tend audit checkout",
  "feature_id": "checkout",
  "reason_codes": ["stale_evidence"],
  "explanation": "Feature \"checkout\": An audit verdict cites a file whose SHA has changed since the verdict was recorded… Run `/tend audit checkout`.",
  "not_chosen": [
    { "feature_id": "user-login", "reason_codes": ["stale_evidence"], "explanation": "…" },
    { "feature_id": "search-filters", "reason_codes": ["blocked"], "explanation": "…" }
  ]
}

Read the full file on GitHub · 189 lines

Files

What ships with it

1 file 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. 8d ago First seen · 189 lines · 55 tokens per session scan A f2c8105e6552

Subscribe to this mod's changes

tend is a skill published in the GitHub repository jahala/umbel (2 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 2,616 once invoked, about $0.0003 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.