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 techwolf-ai/ai-first-toolkit --skill goal-promptgit clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkitWrote 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/techwolf-ai/ai-first-toolkit/goal-prompt)<a href="https://agentmods.dev/skills/techwolf-ai/ai-first-toolkit/goal-prompt"><img src="https://agentmods.dev/badge/skills/techwolf-ai/ai-first-toolkit/goal-prompt.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 18 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00088 | $0.00652 |
| Opus 5 | $0.00044 | $0.00326 |
| Sonnet 5 | $0.00018 | $0.00130 |
| Haiku 4.5 | $0.00009 | $0.00065 |
Grade A, and why
goal-prompt 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 9d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
goal-prompt
Produce a ready-to-paste /goal ... command from whatever the user is trying to accomplish.
Why the shape matters
/goal runs Claude autonomously until a separate fast-model evaluator decides, after a turn, that the condition is met. The evaluator does NOT run commands or read files itself — it only reads Claude's output. So the completion condition must be demonstrable by Claude's own output, never by hidden side effects.
A good goal has three parts
- Measurable end state — one concrete finish line: a test/exit code, a file that must exist, a count, an empty queue, named sections present.
- Stated proof — exactly how Claude demonstrates it: the command to run and its expected result, or the grep/check whose output shows done. Phrase it as "Prove it by showing X."
- Constraints that must not drift — what stays unchanged on the way there: files not to touch, framing to keep, no network/prod, don't modify tests.
How to write it
- One sentence of objective, then
Done when: <end state + proof>, thenConstraints that must not change: <list>. - If the full spec is long, point to a plan/doc file (e.g. a path under
~/.claude/plans/ordocs/) and keep the goal itself scannable. - Make the proof something the transcript can show: prefer
command exits 0+ a summary line, orgrepfor markers, over vague "it works". - Translate conditions the evaluator can't see ("the UI looks good") into an observable check.
- Keep constraints tight enough to stop scope creep, not so rigid they block the obvious path.
Output
Give the user a single fenced block starting with /goal, then 2-3 lines explaining the end state, the proof, and why it's demonstrable. Nothing else.
Example
/goal Add a --json flag to the export CLI per docs/export-json.md. Done when: `pytest tests/test_export.py -q` exits 0 and `python -m app.export --json` prints valid JSON whose top-level keys include "rows" and "meta". Prove it by showing the pytest summary and the piped `... --json | jq keys` output. Constraints that must not change: only edit app/export.py and add tests/test_export.py; do not alter the existing CSV output path; no network.
Its finish line is a passing test plus a schema check, both visible in Claude's transcript; the constraints pin the blast radius so the autonomous run can't wander.
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.
- 9d ago First seen · 33 lines · 88 tokens per session scan A 0796d0760166
goal-prompt is a skill published in the GitHub repository techwolf-ai/ai-first-toolkit (98 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 652 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 2026-08-30.
Other skills, from other repositories
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
i18n-localization
Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.
content-repurposer
Adapt content across platforms with tone/format shifting — blog to social, long to short, text to visual outline. Use when repurposing content for different channels, audiences, or formats.
electron-desktop
Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.