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/khromov/codebay/avatar-contribution-prnpx skills add khromov/codebay --skill avatar-contribution-prgit clone --depth 1 https://github.com/khromov/codebayWrote 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/khromov/codebay/avatar-contribution-pr)<a href="https://agentmods.dev/skills/khromov/codebay/avatar-contribution-pr"><img src="https://agentmods.dev/badge/skills/khromov/codebay/avatar-contribution-pr.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 | $0.00123 | $0.01735 |
| Opus 5 | $0.00062 | $0.00868 |
| Sonnet 5 | $0.00025 | $0.00347 |
| Haiku 4.5 | $0.00012 | $0.00173 |
Grade A, and why
avatar-contribution-pr 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 3d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill lands an avatar submission from codebay's hidden avatar-editor easter egg. The editor (src/components/AvatarEditor.svelte) serializes a drawing via src/avatars/serialize.ts::toIssueUrl, which produces one of two issue shapes depending on whether the user drew a new sprite or redrew an existing one. Both carry the pixel art in a plain fenced block and a byte-identical ready-to-paste src/avatars/<name>.ts module in a ```ts block. This skill reverses that: read the issue, decide create vs. edit, validate the art, and turn it into a merged PR.
1. Fetch the issue and pick the mode
Accept an issue number or URL as input. Fetch it:
gh issue view <number-or-url> --json number,title,body,url
The title prefix decides the mode — the rest of the skill branches on it:
Avatar contribution: <name>→ create: a brand-new sprite. Add a new module and wire it into the catalog.Avatar edit: <name>→ edit: a hand-redraw of an existing AI-generated sprite. Overwrite the existing module in place; the replacement drops therobotflag, so landing it promotes the sprite from robot-drawn to hand-drawn. Do not add a new file or touchindex.ts.
Either way, confirm the body matches what serialize.ts::toIssueUrl produces:
- Body contains a plain fenced block with 8 lines of
#/+/.art (#= on,+= gray,.= off) - Body contains a
```tsfenced block with a fullAvatarArtmodule (import type { AvatarArt } from './types.ts'; ... export default art;)
If the issue doesn't look like this — title is neither prefix, missing code block, art that isn't 8×8 — stop and tell the user what's off rather than guessing at intent or trying to reshape it into something that fits.
2. Extract & validate
Pull name and the module source out of the ```ts block. Before writing anything, validate the art against the same rules src/avatars/avatars.test.ts enforces:
- Exactly 8 rows in
pixels - Each row is exactly 8 characters, only
#,+or.(the editor never emits raw spaces, but treat space as off too if you see one)
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.
- 3d ago First seen · 119 lines · 0 tokens per session scan A 0d4280d76ded
avatar-contribution-pr is a skill published in the GitHub repository khromov/codebay (10 stars, last pushed 4d ago), licensed MIT. It adds 123 tokens to every session and 1,735 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
git-search
List recent git commits across all repos under /Code (excluding .build checkouts). Use when the user asks to show last commits, recent history, or commits across all projects in /Code.
commit-context
Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", "who wrote this", or wants context on a specific location in the codebase.
commit-history
List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants commits with their session context.
create-skill
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
logging-and-error-reporting
How and when to log (log:: levels, safe macros) and report errors to Sentry (reporterror!) in the Warp codebase. Use when adding or reviewing any logging or error reporting — picking a log level, deciding log vs. reporterror!, keeping sensitive data out of logs, or surfacing an error to Sentry.