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/auravixstudio/caelo/debugnpx skills add AuraVixStudio/caelo --skill debuggit clone --depth 1 https://github.com/AuraVixStudio/caeloWhat 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 | $0.00020 | $0.00250 |
| Opus 5 | $0.00010 | $0.00125 |
| Sonnet 5 | $0.00004 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
Debug (reproduce -> isolate -> fix) 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 2d 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.
What it actually says
Debug (reproduce -> isolate -> fix)
Use this to track down a bug methodically.
Steps
- Reproduce. Get a reliable, minimal repro. If you can't reproduce it, gather the exact error, stack trace, inputs, and environment first.
- Isolate. Narrow the failure: read the stack trace, add targeted logging, bisect the input or the recent changes. Form a hypothesis about the root cause.
- Confirm root cause. Verify the hypothesis — don't fix symptoms. State why it fails.
- Fix. Apply the smallest change that addresses the root cause. Avoid unrelated edits.
- Verify + guard. Re-run the repro to confirm the fix, run the broader tests for regressions, and add a test that would have caught this bug.
Notes
- Resist guess-and-check. One confirmed root cause beats five speculative edits.
- Remove temporary logging/instrumentation before finishing.
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.
- 2d ago First seen · 26 lines · 20 tokens per session scan A ea5bd4cdd404
Debug (reproduce -> isolate -> fix) is a skill published in the GitHub repository AuraVixStudio/caelo (22 stars, last pushed 20d ago), licensed Apache-2.0. It adds 20 tokens to every session and 250 once invoked, about $0.0001 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
weftcut
Drive the WeftCut video editor over its MCP tools. Use BEFORE calling any weftcut MCP tool — when the user wants to edit video in WeftCut (cut, trim, arrange a timeline, add captions or voiceover) or author/update a Motif (animated overlay).
seedream
Generate AI images using Volcengine Seedream model. Supports text-to-image (T2I), image editing (I2I), multi-image fusion, and web-search-based generation. Use this skill when the user wants to create, generate, or edit images.
compose:subagent
Use when executing implementation plans with independent tasks in the current session.
seedance
Generate AI videos using Volcengine Seedance model. Supports text-to-video (T2V), image-to-video (I2V), and audio-synced video generation. Use this skill when the user wants to create or generate videos.
compose:plan
Use when you have a spec or requirements for a multi-step task, before touching code.
skill-creator
Use when creating, updating, packaging, or validating an Lfcode skill. Covers normal user-managed skills stored under the Lfcode data directory skills/ / and built-in bundled skills shipped from packages/lfcode/src/skill/lfcode/.bundle/ /.