umbel: Skill for Claude Code

.claude/skills/tend-run/SKILL.md

tend-run is a skill for Claude Code from jahala/umbel. It costs 81 tokens per session (3,568 once invoked), scanned A, original, MIT.

A workflow that takes an already written feature plan and starts its implementation. It can run the plan directly with a command or export it for an outside task system to execute.

In plain words
What is it for?
Use it to execute feature steps through a single agent, Claude Tasks, Relay, Markdown instructions, or GitHub Issues while tracking progress.
Why use it?
It separates carrying out the planned work from checking later whether the result is actually complete and verified.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code.

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 →

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-run/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-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/jahala/umbel/tend-run/github.svg)](https://agentmods.dev/skills/jahala/umbel/tend-run)
Your own site
<a href="https://agentmods.dev/skills/jahala/umbel/tend-run"><img src="https://agentmods.dev/badge/skills/jahala/umbel/tend-run/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 tend-run

Your own site · 80×15
<a href="https://agentmods.dev/skills/jahala/umbel/tend-run"><img src="https://agentmods.dev/badge/skills/jahala/umbel/tend-run.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 3,568 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 $0.03568
Opus 5 $0.00041 $0.01784
Sonnet 5 $0.00016 $0.00714
Haiku 4.5 $0.00008 $0.00357

Measured 10d ago against content hash 1e23bf93d0ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tend-run 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 10d 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-run/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run: Steps -> Execution

Take a feature from plan to execution. Two paths depending on what's appropriate for the project:

Path When
Polyglot run Single-agent flow on a portable artifact. The .tend.html is its own orchestrator: bash <file> run iterates steps[] and invokes the agent CLI per step, then runs smoke.
External adapter Multi-agent or external orchestrator. tend_output_execution_plan emits the plan in the adapter's native format (Claude Tasks bundle, Relay workflow, Markdown spec, GitHub Issues batch); the orchestrator consumes it.

This skill never writes audit.result or status = "verified" - that belongs to tend-audit, which evaluates the evidence before the verdict. Run finishes the implementation; audit determines whether it's actually done.

What this skill assumes

  • The feature has steps written (output of /tend plan). Each step's Test: block has been authored.
  • Each step traces to specific check IDs via traces_to. Untraced steps must be command/worktree steps (no test discipline applies).
  • For steps tracing to checks with validates_job set, the bound persona-job's validation clause is available to inject into the agent's RED prompt — the failing test asserts against that validation, not a paraphrase.
  • An execution adapter is configured (docs/tend/adapters/*.json) or the user has chosen one for this run.

Fits the whole

Layer Role
Polyglot bash <file>.tend.html run orchestrates the build; bash <file>.tend.html smoke verifies
MCP tend_output_execution_plan emits adapter-native plans; tend_update_feature writes step status during run
Filesystem Reads feature data via `bash data

Read the full file on GitHub · 281 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. 10d ago First seen · 281 lines · 81 tokens per session scan A 1e23bf93d0ae

Subscribe to this mod's changes

tend-run is a skill published in the GitHub repository jahala/umbel (2 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 3,568 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.