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 monkilabs/opencastle --skill self-improvementgit clone --depth 1 https://github.com/monkilabs/opencastleWrote 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/monkilabs/opencastle/self-improvement)<a href="https://agentmods.dev/skills/monkilabs/opencastle/self-improvement"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/self-improvement/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/monkilabs/opencastle/self-improvement"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/self-improvement.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00134 | $0.01542 |
| Opus 5.5 | $0.00054 | $0.00617 |
| Sonnet 5.5 | $0.00027 | $0.00308 |
| Haiku 4.5 | $0.00013 | $0.00154 |
Grade A, and why
self-improvement 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 12d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Improvement
Lessons are the team's memory. A lesson is a file in .opencastle/lessons/, committed with the change you made, so the team reviews it in that pull request. .opencastle/LESSONS-LEARNED.md is the index, and Claude Code, VS Code, Cursor and Windsurf load a copy of it before every task; both are rewritten from the lesson files — never edit them by hand.
The team's or the user's
Decide when you learn it, by how you save it. Nobody sorts memories afterwards.
In Claude Code and VS Code, save it in your own memory as you normally do. When the session ends, OpenCastle copies what is about the project into a lesson, and leaves what is about the user. In any other assistant, record what is about the project as a lesson yourself (below).
| It is about | Save it as | For example |
|---|---|---|
| The project: true for anyone working in this repository | About the project (a correction, a project note, a pointer to where something lives) | pnpm build fails without CI=1 set; every migration ships with a down file; the staging API allows 10 requests a second; the user says "we never use default exports" |
| The user: true for them, wherever they work | About the user. It stays theirs and never becomes a lesson | They want short answers; they use fish; their role; their editor; paths on their machine |
| A procedure you had to work out, which no skill covers | A team skill, written in the same change (below) | How to run the end-to-end tests against a local database; the steps to release the mobile app |
| Every repository in the organisation | About the project, saying it holds in every repository; it graduates into the baseline's skill (below) | The company's deploy pipeline needs a manual approval; an internal service's API contract |
| This task only | Nothing | A one-off workaround; a guess you have not confirmed |
- Confirmed means the fix worked, the code shows it, or the user said so. A suspicion is not worth saving.
- A correction from the user: about the code or the project, it is about the project; about how they want you to work with them, it is about the user.
- A lesson copied from memory is category
general, severitymedium, and cites nothing. When your task touches one, set them in its file, and cite the code withnpx opencastle lesson verify <id> --cite <path>.
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.
- 12d ago Changed · +9 lines · +16 tokens per session 414e03192347
- 20d ago Changed · +17 lines · +50 tokens per session f7c3ce5180a3
- 21d ago Changed · -25 lines · +9 tokens per session 5b96b343a78f
- 23d ago Changed · -26 tokens per session 4a27eaca6b12
- 24d ago Changed · +15 lines · +15 tokens per session 4efc2b2be746
- 1mo ago First seen · 58 lines · 70 tokens per session scan A 27fa4a242665
self-improvement is a skill published in the GitHub repository monkilabs/opencastle (80 stars, last pushed 7d ago), licensed MIT. It adds 134 tokens to every session and 1,542 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
session-handoff-prompt
Create a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session. Use when the user asks for a handoff prompt, restart prompt, continuation prompt, context transfer, fresh-session resume, or a compact summary for opening a new session. Do not use for ordinary summaries…
pause-and-resume
Cooperatively pause unfinished work in the current session, leave a precise continuation checkpoint, and resume from it when the user later says continue. Use only when the user explicitly requests this pause workflow. Do not use for crashes, app shutdown, new-session handoffs, or ordinary task summaries.
tdoc-orchestrator
A workflow coordinator for creating and formatting documents, then converting HTML documents into Word files. It identifies the user's document task and sends each stage to the appropriate specialist.
tencent-docs
A tool for creating, editing, reading, searching, and managing files in personal Tencent Docs, an online document service for individual QQ or WeChat accounts. It supports documents, spreadsheets, slides, and other listed file types.
tencent-saas-docs
A tool for creating, editing, reading, searching, and managing documents in Tencent Docs Enterprise, an online document service for business accounts. It works with documents, spreadsheets, slides, diagrams, and related files when an enterprise account is available.