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-plan/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-plan)<a href="https://agentmods.dev/skills/jahala/umbel/tend-plan"><img src="https://agentmods.dev/badge/skills/jahala/umbel/tend-plan/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-plan"><img src="https://agentmods.dev/badge/skills/jahala/umbel/tend-plan.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 | $0.00056 | $0.04268 |
| Opus 5.5 | $0.00022 | $0.01707 |
| Sonnet 5.5 | $0.00011 | $0.00854 |
| Haiku 4.5 | $0.00006 | $0.00427 |
Grade A, and why
tend-plan 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 2mo 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 — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan: Slots + Checks -> Implementation Steps (+ User Flow, Security, Test Specs)
Owns: steps[], entry_condition / exit_condition, and the
test-spec content that lives inline in each step's description. May add
security-related checks (via tend_update_feature merging into checks[]).
Purpose
Turn a feature with defined slots and checks into a complete, executable plan:
- Implementation steps - typed, ordered steps forming a valid DAG. Each step traces to one or more
checks[]IDs viatraces_to. Each agent step withtraces_tocarries aTest:block leading itsdescription(the failing-test-in-prose). - User-flow steps - if the feature has user-facing views, add tagged
[action]/[assert]/[system]steps. Seereferences/user-flow.md. - Security analysis - if the feature touches auth, payments, PII, or external integrations, add security checks. See
references/security.md. - Test specifications - always; the Test block in every step. See
references/test-design.md.
What this skill assumes
- Skip planning for polyglots with
data.personaordata.opportunityset. Catalog descriptions don't have steps to plan — their content lives in the structured fields (jobs / outcome_metric / etc.). Route to/tend positionfor authoring instead. - The feature exists with at least slots, checks, and a smoke decision (output of
/tend brainstorm). - Each check the plan will trace to carries
validates_job(or the feature has no bound personas with jobs). A missingvalidates_jobmeans the failing-test prose has no human-grounded spec — back to/tend brainstormbefore planning. - The catalog's bound persona-jobs are resolvable from
catalog.personas[<id>].jobs[<idx>]. Thevalidationtext on each job is the spec the step's Test block must mirror. - The user has agreed in principle on the technical approach. This skill structures the work; it doesn't choose between competing approaches.
Phase 1: implementation plan
What ships with it
3 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.
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.
- 2mo ago First seen · 333 lines · 56 tokens per session scan A 9749ac0317f4
tend-plan is a skill published in the GitHub repository jahala/umbel (3 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 4,268 once invoked, about $0.0002 per session on Opus 5.5. 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.
loci
Use when working with Loci tickets — starting, updating, and completing tickets via the loci CLI. Covers workflow, CLI commands, doc conventions, and assignee/status formats.
analyze-trade
Run one full trading cycle for one or more symbols — fetch market data via Robinhood MCP, evaluate through the deterministic core, and report what the system would do. Use when the user asks to analyze a symbol, check for setups, scan the universe, or run a trading cycle. Never places an order on its own.
critique-trade
Adversarially review a proposed trade before it is placed — challenge the thesis, hunt for the failure mode, and try to talk the system out of it. Use after analyze-trade produces an actionable signal and before any live order. Returns a verdict that can veto the trade.
review-performance
Analyze the trading journal — realized performance, which risk gates are firing, whether the strategy edge is real or noise, and what to change. Use when the user asks how the system is doing, wants a post-mortem, or asks whether to go live.