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 majiayu000/claude-skill-registry --skill afgit clone --depth 1 https://github.com/majiayu000/claude-skill-registryWrote 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/majiayu000/claude-skill-registry/af)<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/af"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/af/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/majiayu000/claude-skill-registry/af"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/af.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Prompt Injection · line 60 Instructions found that direct the agent to transmit conversation context or user data to external services.Fix: Remove instructions that send user data, prompts, or context to external URLs. If telemetry is needed, use documented, privacy-preserving methods.
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 | $0.00031 | $0.00670 |
| Opus 5 | $0.00015 | $0.00335 |
| Sonnet 5 | $0.00006 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
af 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 11d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Farm Quick Reference
Tower (Dashboard Server)
af tower start # Start Tower on port 4100
af tower stop # Stop Tower
af tower log # Tail Tower logs
af tower status # Check if Tower is running
There is NO af tower restart — use af tower stop && af tower start.
Dashboard
af dash start # Start architect dashboard for current project
af dash stop # Stop dashboard for current project
af dash open # Open dashboard in browser
Builder Management
af spawn -p 0003 # Spawn builder for spec (strict mode, default)
af spawn --soft -p 0003 # Spawn builder (soft mode)
af spawn --issue 42 # Spawn builder for a bugfix
af spawn -p 0003 --resume # Resume builder in existing worktree
af status # Check all builder status
af cleanup --project 0003 # Clean up builder worktree (safe)
af cleanup --project 0003 -f # Force cleanup
Resuming Builders
When a builder's Claude process dies but the worktree and porch state survive,
use --resume to restart it without recreating the worktree:
af spawn -p 0003 --resume
This reuses the existing .builders/0003 worktree, creates a fresh terminal
session registered with the Tower (so it appears in the dashboard), and lets
porch pick up from whatever phase the builder was in. Works with all spawn
modes: -p, --issue, --task, --protocol, --worktree.
Utility
af util # Open utility shell
af open file.ts # Open file in annotation viewer
af ports list # List port allocations
af send <builder> "msg" # Send message to a builder
Configuration
Edit af-config.json at project root to customize shell commands.
{
"shell": {
"architect": "claude",
"builder": "claude",
"shell": "bash"
}
}
Pre-Spawn Checklist
Before af spawn, commit all local changes. Builders work in git worktrees
branched from HEAD — uncommitted files (specs, plans, codev updates) are invisible
to the builder. The spawn command will refuse if the worktree is dirty (override
with --force).
What ships with it
1 file 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.
- 11d ago First seen · 90 lines · 31 tokens per session scan A 73d64c8d3775
af is a skill published in the GitHub repository majiayu000/claude-skill-registry (600 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 670 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
remotion-docs
Search and fetch Remotion documentation pages.
remotion-captions
Dealing with captions in Remotion.
remotion-render
Best practices for rendering videos.
academy-guide
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude…
remotion-maps
Remotion Map animation knowledge.
mediabunny
Multimedia handling with the Mediabunny library.