Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add smixs/iva-agent --skill goalgit clone --depth 1 https://github.com/smixs/iva-agentWrote 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/smixs/iva-agent/goal)<a href="https://agentmods.dev/skills/smixs/iva-agent/goal"><img src="https://agentmods.dev/badge/skills/smixs/iva-agent/goal/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/smixs/iva-agent/goal"><img src="https://agentmods.dev/badge/skills/smixs/iva-agent/goal.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 | $0.00060 | $0.00887 |
| Opus 5.5 | $0.00024 | $0.00355 |
| Sonnet 5.5 | $0.00012 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
goal 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 yesterday.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
A goal repeats checks until an observable result and the owner's closure.
Use remind for a message or action at a named time, helper for work that
finishes in one run. Watch tells the owner about new items under an agreed
responsibility; a goal checks by schedule and acts within may until closure.
The owner sees the word "goal" in confirmations and buttons. CORE goals remain
standing context in CORE, while this tool follows a particular result.
Set up
- Read the request and context. Identify the observable result, sources, people involved and when to check again. Ask once for missing information that determines the result or boundaries. Reuse what the owner already said.
- Write
textas the result andplanas the next check and its sources. Convert the owner's next-check time to a form accepted by the tool.
Boundaries
Before start, make actions on the owner's behalf explicit. Copy only the
owner's words into may: whom to contact, what to send, whether to show the
text before sending. If correspondence requires an unstated permission, ask
once before starting. For observation and drafts, pass may: "" explicitly.
Tell the owner that you will look and prepare drafts and sending needs their
permission. Later permission updates may with their words, preserving the
existing boundary.
Confirm and follow
- Call
goal startwithtext,may,planand an agreednext_check. Read the receipt. Name the result, saved boundary, check frequency and any waiting reason. Scheduled checks continue when Watch is off. Build the nearest start from nextCheckAtMs, quietHour, quietToHour and checks_today: wait until quiet hours end, or until the next day when the receipt's checksPerDay is reached. Take frequency from intervalMs. - On "how's it going?", call
goal list. Read any untold row withhelper outcome. Explain the plan, next check, checks today and pause. - Retell a check's Outcome with its substance, evidence, completed actions
and question. Call
goal listbefore choosing buttons by current status. Forproposed, ask "Goal «…» выполнен?" and offer "Закрыть goal" and "Продолжай". Forpaused, offer "Продолжай". Use the owner's language andrich-replies; button data names the goal id and action. An absent goal gets a text reply. The owner's instruction or tap callsgoal closeorgoal resume; a stale button gets the tool's refusal in plain words. - Put the owner's answer into
planthroughgoal update, keeping sources and agreed boundaries. New permission also updatesmay. "Проверь сейчас" callsgoal updatewithnext_check: "now". After the receipt, say you will write only if something new is found; a check with no news stays silent. Promise to report a failure only after the third consecutive failure; the first two stay silent. Repeat a named time in the confirmation. - Tell an expired pause once in the conversation and offer to continue. A third consecutive failure has its own Outcome to retell with the pause.
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.
- yesterday First seen · 68 lines · 60 tokens per session scan A cb929981952f
goal is a skill published in the GitHub repository smixs/iva-agent (240 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 887 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 2026-10-15.
Other skills, from other repositories
linear
Manage Linear issues, projects, and teams via the GraphQL API. Create, update, search, and organize issues. Uses API key auth (no OAuth needed). All operations via curl — no dependencies.
notion
Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal.
github
GitHub CLI (gh) for repository management, issues, pull requests, releases, workflows, search, gists, and API access. Use when the user asks about any GitHub operation — creating repos, forking, cloning, PR workflows, issue triage, CI/CD runs, code search, release management, or direct API calls. Keywords: github, gh…
building-growth-team
Help users determine when to hire growth talent, which profiles to prioritize, and how to structure the team for maximum leverage across the user journey.
engineering-health
Help users build a sustainable engineering culture by measuring health through frameworks like Core 4, managing technical debt as leverage, and optimizing workflows with AI tools.
org-design
Help users design high-performing product and engineering organizations by choosing the right reporting models, team sizes, and cross-functional partnerships. It focuses on reducing friction and maximizing ownership through structural clarity.