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-position/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-position)<a href="https://agentmods.dev/skills/jahala/umbel/tend-position"><img src="https://agentmods.dev/badge/skills/jahala/umbel/tend-position/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-position"><img src="https://agentmods.dev/badge/skills/jahala/umbel/tend-position.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 | $0.00119 | $0.05113 |
| Opus 5 | $0.00060 | $0.02557 |
| Sonnet 5 | $0.00024 | $0.01023 |
| Haiku 4.5 | $0.00012 | $0.00511 |
Grade A, and why
tend-position 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.
How it starts
The opening of the file, as written. The whole thing — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Position: Who is this for, what job do they hire it for
Owns: catalog.personas[] (id, name, description, archetype,
jobs[]) and catalog.opportunities[] (id, description, value,
confidence, source, signals, personas: string[]) on the garden
polyglot.
Job indexing is a load-bearing contract. Each persona's
jobs[]is an ordered array. Downstream checks anchor to a specific job viavalidates_job: "<persona_id>:<job_index>"—"founder:0"means "persona founder, first Klement Job Story." Reordering jobs after publication silently retargets every check pointing at them, so treat the array like an append-only list once features start referencing it. If a job must be reordered or removed,/tend changerequires an explicit reindex map so it can rewrite every dependentvalidates_job.
What this skill assumes
- The garden polyglot exists and has at least a draft bet (the project knows roughly what it is).
- The user has some sense of who the project is for — at minimum a few interview notes, sales-call snippets, or strong founder intuition. This skill structures what the user already knows; it does not generate ICPs from nothing.
- It's OK if the catalog has shallow personas (
nameonly) — this skill fills inarchetype,jobs[], andopportunity.personasfrom there. - Downstream skills (
/tend brainstorm,/tend audit) will be unwired without this skill's output. Run this before they need it.
Purpose
Tend's six slots tell you what you're building and why technically. They don't tell you who you're building it for or what job that person hires your product to do in a specific moment of their week. Without that, every downstream artifact — feature pages, narratives, evals — drifts toward technical-taxonomy voice.
This skill plants the spine:
- ICP archetypes — one phrase per persona that names a real human with real stakes. Not roles ("Backend Engineer"), but situated archetypes ("Solo founder running a SaaS side project on weekends; values speed over polish; can't justify a day of tooling").
- Klement Job Stories — 3–5 per persona, in the form: "When [situation], because [motivation], we believe [outcome]. We'll know we got it right when [validation]."
- Refined opportunities — pains felt by which persona, value level, confidence (and source / signals if known).
- Scenario seeds — 2–3 concrete moments per persona (a sentence or
two each), captured in the persona's
descriptionor jobs. These are the openers tend-narrate uses to start feature pages with a story rather than a label.
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.
- 8d ago First seen · 448 lines · 119 tokens per session scan A cba18451d8cf
tend-position is a skill published in the GitHub repository jahala/umbel (2 stars, last pushed 3d ago), licensed MIT. It adds 119 tokens to every session and 5,113 once invoked, about $0.0006 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-failing-tests-immediately-after-test-gate-failure
When delegating a task affected by this skill, include.
run-test-suite-after-registration-changes
When delegating a task affected by this skill, include.