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.
curl -O https://raw.githubusercontent.com/jahala/umbel/master/.claude/skills/tend-run/SKILL.mdgit clone --depth 1 https://github.com/jahala/umbelWrote 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/jahala/umbel/tend-run)<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.
<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>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 | $0.00081 | $0.03568 |
| Opus 5 | $0.00041 | $0.01784 |
| Sonnet 5 | $0.00016 | $0.00714 |
| Haiku 4.5 | $0.00008 | $0.00357 |
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.
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'sTest: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_jobset, the bound persona-job'svalidationclause 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 |
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.
- 10d ago First seen · 281 lines · 81 tokens per session scan A 1e23bf93d0ae
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.
Other skills, from other repositories
factory-handoff
Hand one exact agent-ready ticket to the central Factory runtime over the configured SSH forced-command boundary. Use when an operator asks to hand off an existing ticket or a prose request instead of implementing it in the current session.
ticket-spec
Turn a raw Linear Triage ticket into a fully specified ai:agent-ready one by exploring the codebase. Use when specifying, refining, or promoting tickets, or when asked why a ticket isn't dispatchable.
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
bundle-safety
Bundle transform safety — minification variant selection, consumer-constraint verification, identifier preservation, and namespace re-export coverage for build output.
run-test-suite-after-registration-changes
When delegating a task affected by this skill, include.
run-failing-tests-immediately-after-test-gate-failure
When delegating a task affected by this skill, include.