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 agentmods add skills/techwolf-ai/ai-first-toolkit/techwolf-logonpx skills add techwolf-ai/ai-first-toolkit --skill techwolf-logogit 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/techwolf-logo)<a href="https://agentmods.dev/skills/techwolf-ai/ai-first-toolkit/techwolf-logo"><img src="https://agentmods.dev/badge/skills/techwolf-ai/ai-first-toolkit/techwolf-logo.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.01740 |
| Opus 5 | $0.00018 | $0.00870 |
| Sonnet 5 | $0.00007 | $0.00348 |
| Haiku 4.5 | $0.00004 | $0.00174 |
Grade A, and why
techwolf-logo 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TechWolf Logo Skill
This skill bundles the official TechWolf logo assets. Always use these files when a TechWolf logo is needed in any output.
CRITICAL RULE
NEVER generate, recreate, or approximate the TechWolf logo from memory. The logo contains precise SVG paths that cannot be reproduced correctly by guessing. Always read and copy the exact files from this skill directory.
Logo Variants
| File | Description | Use when |
|---|---|---|
techwolf-logo-dark |
Dark text + aquamarine circle | Light backgrounds |
techwolf-logo-white |
White text + aquamarine circle | Dark backgrounds (most common in TechWolf UI) |
techwolf-logo-mono-dark |
All dark (single color) | Monochrome contexts on light backgrounds |
techwolf-logo-mono-white |
All white (single color) | Monochrome contexts on dark backgrounds |
Each variant is available as both .svg (vector, preferred for web) and .png (raster, for documents/images).
How to Use
In HTML / Web outputs
- Read the appropriate SVG file from this skill directory
- Embed the SVG content inline in your HTML
<!-- Example: read techwolf-logo-white.svg and paste its content here -->
<div class="logo">
<!-- paste exact SVG content from the file -->
</div>
In documents, images, or other outputs
- Copy the appropriate PNG file to your output directory
- Reference it from your document
currentColor version (for HTML where logo color should inherit from parent)
When you need the logo to inherit its color from a parent CSS color property (e.g., in slide decks or themed UIs), use this inline SVG. The text paths use currentColor and the "O" circle stays aquamarine (#63FFD9):
<svg width="100" height="11" viewBox="0 0 151 16" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M13.7243 4.72539H9.288V15.5364H4.9785V4.72539H0.5V1.46289H13.7243V4.72539Z" fill="currentColor"/><path d="M31.4468 12.2739V15.5364H19.9336V1.46289H31.1722V4.72539H24.2431V7.00701H29.7779V10.035H24.2431V12.2739H31.4468Z" fill="currentColor"/><path d="M50.3094 11.3574C49.9292 12.8642 49.1898 13.973 48.0912 14.6838C47.0069 15.3946 45.6549 15.7499 44.0352 15.7499C42.5988 15.7499 41.3525 15.4657 40.2962 14.8971C39.254 14.3284 38.4512 13.4968 37.8879 12.4022C37.3245 11.3076 37.043 10.0069 37.043 8.5C37.043 6.99313 37.3245 5.6995 37.8879 4.61911C38.4512 3.5245 39.254 2.69289 40.2962 2.12427C41.3384 1.54142 42.5777 1.25 44.0142 1.25C45.5915 1.25 46.9365 1.59118 48.0491 2.27353C49.1616 2.94166 49.8728 3.95809 50.1827 5.32279L46.4435 6.83676C46.2887 5.96961 46.0352 5.37966 45.683 5.06691C45.3309 4.73995 44.8169 4.57647 44.141 4.57647C43.2818 4.57647 42.62 4.90344 42.1551 5.55735C41.7045 6.21127 41.4792 7.19215 41.4792 8.5C41.4792 11.1157 42.3524 12.4235 44.0987 12.4235C44.8028 12.4235 45.338 12.2601 45.7041 11.9331C46.0844 11.5919 46.3379 11.0517 46.4646 10.3125L50.3094 11.3574Z" fill="currentColor"/><path d="M69.5085 1.46289V15.5364H65.1779V10.0776H60.6572V15.5364H56.3477V1.46289H60.6572V6.8151H65.1779V1.46289H69.5085Z" fill="currentColor"/><path d="M84.0013 15.5364H79.2271L75.2344 1.46289H79.882L81.8465 12.1033L84.0436 1.46289H87.8461L90.1487 12.0607L92.0711 1.46289H96.5495L92.557 15.5364H87.9094L86.5574 9.52318L85.987 6.0048H85.9237L85.3532 9.52318L84.0013 15.5364Z" fill="currentColor"/><path d="M115.236 8.25098C115.236 12.3931 112.012 15.751 108.034 15.751C104.056 15.751 100.832 12.3931 100.832 8.25098C100.832 4.10885 104.056 0.750977 108.034 0.750977C112.012 0.750977 115.236 4.10885 115.236 8.25098Z" fill="#63FFD9"/><path d="M133.04 12.2739V15.5364H122.098V1.46289H126.407V12.2739H133.04Z" fill="currentColor"/><path d="M143.591 4.72539V7.17759H149.125V10.4401H143.591V15.5364H139.281V1.46289H150.499V4.72539H143.591Z" fill="currentColor"/></svg>
What ships with it
8 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.
- 4d ago First seen · 59 lines · 36 tokens per session scan A 345914e215ae
techwolf-logo is a skill published in the GitHub repository techwolf-ai/ai-first-toolkit (96 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,740 once invoked, about $0.0002 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.
clarify
Adaptive requirements clarification with auto-depth routing. Shallow (Q&A) for simple tasks, Deep (exploration + DRAFT + PLAN) for complex ones. Escalates automatically when ambiguity persists.
auditing-aws-s3-bucket-permissions
Systematically audit AWS S3 bucket permissions to identify publicly accessible buckets, overly permissive ACLs, misconfigured bucket policies, and missing encryption settings using AWS CLI, S3audit, and Prowler to enforce least-privilege data access controls.
correlating-security-events-in-qradar
Correlates security events in IBM QRadar SIEM using AQL (Ariel Query Language), custom rules, building blocks, and offense management to detect multi-stage attacks across network, endpoint, and application log sources. Use when SOC analysts need to investigate QRadar offenses, build correlation rules, or tune…