Borrowing it
Nothing to install: this file belongs to sageox/agent-toolkit. 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/sageox/agent-toolkit/main/.agents/skills/agent-avatar/SKILL.mdgit clone --depth 1 https://github.com/sageox/agent-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/sageox/agent-toolkit/agent-avatar)<a href="https://agentmods.dev/skills/sageox/agent-toolkit/agent-avatar"><img src="https://agentmods.dev/badge/skills/sageox/agent-toolkit/agent-avatar/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/sageox/agent-toolkit/agent-avatar"><img src="https://agentmods.dev/badge/skills/sageox/agent-toolkit/agent-avatar.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 | $0.00069 | $0.01185 |
| Opus 5 | $0.00034 | $0.00593 |
| Sonnet 5 | $0.00014 | $0.00237 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade A, and why
agent-avatar 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create an agent avatar
Use the toolkit's existing character brief, shared house style, generator, and profile publisher. Preserve durable identity separately from rendering so the roster can be restyled without redesigning every character.
Inspect the identity first
Read the agent's AGENTS.md, profile.json, and avatar.md. Read
design-system.md when drafting or substantially revising the
character. Use the real job and persona as evidence; do not design from the name alone.
Keep these layers separate:
avatar.mdowns role metaphor, silhouette, signature prop, wardrobe and palette intent, background hue, expression, posture, and one role-specific joke.packages/cli/src/avatar-house-style.txtowns composition, line, lighting, crop, and the rest of the shared rendering system.profile.jsonselectsavatar.svgoravatar.pngfor publication.
Do not copy the house style into each brief. Do not reduce identity to hex colors or model-specific prompt syntax.
Design for recognition
Make the avatar pass all of these tests:
- The face, silhouette, signature prop, and joke read in a 32 px circular crop.
- Eyes remain open and visible; props route behind or beside the face.
- The expression and posture match the behavioral persona.
- The silhouette remains distinct in grayscale.
- A total art-style swap leaves the character recognizable.
- No text, logo, detailed scenery, or decorative frame is needed for recognition.
Prefer one strong prop and one visual joke over many small clues. Keep humor warm and tied to the work, not to protected traits or humiliation.
Generate new artwork
For a new guided agent, the integrated flow is the user's to run in their own terminal:
./bin/sageox-agent create --name <agent-name>
The guided flow generates three candidates and pauses for a human selection. Selecting
between candidates needs a terminal, so more than one candidate is something you hand to the
human to run — asking for several from a tool shell fails with multiple avatar candidates need an interactive terminal for selection.
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.
- yesterday First seen · 115 lines · 69 tokens per session scan A 7c7b4469e638
agent-avatar is a skill published in the GitHub repository sageox/agent-toolkit (10 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 1,185 once invoked, about $0.0003 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 2026-09-10.
Other skills, from other repositories
helm-expert
Expert-level Helm 3 package management, chart development, templating, and production operations. Use when the user mentions Kubernetes, package manager, charts, templates, or deployment, or when the task involves Helm Architecture, Chart Structure, Values.yaml, or Helm Hooks.
helm
A guide to Helm, a package manager for Kubernetes applications. Helm uses reusable packages called Charts to install, configure, upgrade, inspect, and remove groups of Kubernetes resources.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
article
Write a publication-ready article in one of three angles - a trending long-form piece, a watched-repo thesis, or a project-through-a-lens essay. Optional Replicate hero image with --visual.
fork-fleet
Fork divergence monitor - tracks where the fleet's active forks diverge in CODE (unique commits, new/modified skills) and CONFIG (enable/var/model/schedule vs upstream), gated on real change.