Caliber is a tool that generates and continuously updates AI context and configuration files for software repositories, including CLAUDE.md, AGENTS.md, and platform-specific rules. Development teams use it to keep coding agents aligned with the current codebase across tools such as Claude Code, Cursor, Codex, OpenCode, and GitHub Copilot. Its catalogue entries include skills, hooks, rules, instructions, and settings for configuring that workflow.
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 caliber-ai-org/ai-setup --skill save-learninggit clone --depth 1 https://github.com/caliber-ai-org/ai-setupWrote 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/caliber-ai-org/ai-setup/save-learning)<a href="https://agentmods.dev/skills/caliber-ai-org/ai-setup/save-learning"><img src="https://agentmods.dev/badge/skills/caliber-ai-org/ai-setup/save-learning/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/caliber-ai-org/ai-setup/save-learning"><img src="https://agentmods.dev/badge/skills/caliber-ai-org/ai-setup/save-learning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Prompt Injection · line 48 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00071 | $0.00633 |
| Opus 5.5 | $0.00028 | $0.00253 |
| Sonnet 5.5 | $0.00014 | $0.00127 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
save-learning 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Learning
Save a user's instruction or preference as a persistent learning that will be applied in all future sessions on this project.
Instructions
- Detect when the user gives an instruction to remember, such as:
- "remember this", "save this", "always do X", "never do Y"
- "from now on", "going forward", "in this project we..."
- Any stated convention, preference, or rule
- Refine the instruction into a clean, actionable learning bullet with
an appropriate type prefix:
**[convention]**— coding style, workflow, git conventions**[pattern]**— reusable code patterns**[anti-pattern]**— things to avoid**[preference]**— personal/team preferences**[context]**— project-specific context
- Show the refined learning to the user and ask for confirmation
- If confirmed, run:
For personal preferences (not project-level), addcaliber learn add "<refined learning>"--personal:caliber learn add --personal "<refined learning>" - Stage the learnings file for the next commit:
git add CALIBER_LEARNINGS.md
Examples
User: "when developing features, push to next branch not master, remember it"
-> Refine: **[convention]** Push feature commits to the \next` branch, not `master` -> "I'll save this as a project learning: **[convention]** Push feature commits to the \next` branch, not `master`
Save for future sessions?"
-> If yes: run caliber learn add "**[convention]** Push feature commits to the next branch, not master"
-> Run git add CALIBER_LEARNINGS.md
User: "always use bun instead of npm"
-> Refine: **[preference]** Use \bun` instead of `npm` for package management`
-> Confirm and save
User: "never use any in TypeScript, use unknown instead"
-> Refine: **[convention]** Use \unknown` instead of `any` in TypeScript`
-> Confirm and save
When NOT to trigger
- The user is giving a one-time instruction for the current task only
- The instruction is too vague to be actionable
- The user explicitly says "just for now" or "only this time"
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.
- 1mo ago First seen · 61 lines · 71 tokens per session scan A f8af7becc6a3
save-learning is a skill published in the GitHub repository caliber-ai-org/ai-setup (1,309 stars, last pushed 25d ago), licensed MIT. It adds 71 tokens to every session and 633 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
memory
Persistent, token-efficient project memory. When ON, maintains a .shob/memory/ folder of structured .md files so the full context of the project is NEVER lost across responses, sessions, or context compaction. Uses progressive disclosure — routes through a lightweight INDEX and loads only the files a task needs…
atomic-wiki
Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the block in /.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via atomic wiki bucket add rather than a…
ai-session-search
Search, recover, inspect, export, and analyze local AI session history with AI Session Search (aise) across Claude Code, Claude Desktop local agent, Codex, Cursor, Antigravity, Pi coding agent, Prime Agent, Google AI Studio, and Gemini CLI. Use when asked to "find prior AI work", "recover context after compaction"…
ccs
Search local Claude Code, Codex, and Cursor user-prompt history (read-only). Use when you need a past prompt, want to grep coding-agent session text, or pipe prompt history as JSON.
write-terva-lore
Author terva lore. Lore is context that a person authors in files. terva injects it only when it is keyword-relevant, or always-on. Use to create/add/write lore, "world info", a lorebook entry, keyed background, or a book of facts for a character.
handoff
Compact the current session into a handoff document. A fresh session or another agent can pick it up with no need to re-derive context. Use when asked to hand off, hand over, wrap up for another session or agent, or park work mid-stream.