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 oxbshw/watch-skill --skill learning-from-mistakesgit clone --depth 1 https://github.com/oxbshw/watch-skillWrote 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/oxbshw/watch-skill/learning-from-mistakes)<a href="https://agentmods.dev/skills/oxbshw/watch-skill/learning-from-mistakes"><img src="https://agentmods.dev/badge/skills/oxbshw/watch-skill/learning-from-mistakes.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.00347 |
| Opus 5 | $0.00037 | $0.00173 |
| Sonnet 5 | $0.00015 | $0.00069 |
| Haiku 4.5 | $0.00007 | $0.00035 |
Grade A, and why
learning-from-mistakes 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 today.
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
Learning from mistakes
When a video answer turns out wrong, the correction is worth more than an apology. Report it and Watch Skill learns locally — the mistake is classified, stored as a lesson, injected into future similar questions, and where possible the original question is immediately re-asked to confirm the lesson actually fixes it.
Report a correction
The moment the user corrects a video answer, run:
watch-skill lessons add <video_id> "<question>" "<the wrong answer>" "<the correction>"
The output includes the lesson (error_class, guidance) and, when the
question was re-asked, whether the corrected answer now comes back —
tell the user which it was. Nothing is uploaded; lessons live in
~/.watch-skill/.
See what has been learned
watch-skill lessons list
The savings meter
watch-skill stats
Lifetime token economics: what text-first answering and the semantic cache have saved versus stuffing raw frames into context. Quote real numbers from it when the user asks whether any of this is worth it.
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.
- today Changed 9bad1472f8e8
- 8d ago First seen · 46 lines · 75 tokens per session scan A 7d19234ab57d
learning-from-mistakes is a skill published in the GitHub repository oxbshw/watch-skill (337 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 347 once invoked, about $0.0004 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
screenpipe-chats
Search what was said in existing screenpipe, Codex, Claude, Cursor, and Gemini CLI chats, then continue or steer one exact chat when the user explicitly asks. Use for requests about finding another agent conversation, recalling what an agent said, or sending work to one.
render-html-report
Produce a human-facing visual report — a chart, dashboard, scorecard, or styled summary — that renders as a live page in the screenpipe viewer instead of plain text. Use when the task asks for a visual/graphical output rather than a plain note; do NOT use for plain text or raw data (prefer a markdown note for those).
screenpipe-team
Use the native Screenpipe CLI to query Enterprise team activity or safely preview, deploy, and schedule managed team Pipes. Injected only by the Enterprise app for active admins.
cerul
Use Cerul when a user needs cited evidence from video or long-form media, or asks what was said, shown, or presented.
segment-anything-model
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
stable-diffusion-image-generation
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.