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/nyaomaru/is-kit/learnnpx skills add nyaomaru/is-kit --skill learngit clone --depth 1 https://github.com/nyaomaru/is-kitWhat 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 | $0.00038 | $0.00976 |
| Opus 5 | $0.00019 | $0.00488 |
| Sonnet 5 | $0.00008 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
learn 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 yesterday.
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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/learn - Capture Reusable is-kit Patterns
Analyze the current session and capture reusable knowledge for this TypeScript type-guard library.
Auto-Activation Criteria
Consider auto-activating this skill when:
- A non-trivial bug was fixed in runtime guard behavior or type inference.
- A public API design decision was made and validated with tests.
- A tricky TypeScript modeling pattern was discovered.
- A runtime/type parity issue was diagnosed and resolved.
- The session produced reusable guidance about tests, docs, or release safety for this library.
Do not activate for:
- trivial typo fixes
- one-line doc wording changes
- obvious refactors with no reusable lesson
- patterns already documented in
.codex/skills/learn/learned/
Manual Trigger
Run /learn after finishing a meaningful implementation, refactor, or debugging session in is-kit.
What To Extract
1. Public API Design Patterns
- What API was added or changed?
- Why was that shape chosen over alternatives?
- What backward-compatibility constraint mattered?
- How should similar future APIs be designed?
Project-relevant examples:
- Distinguishing key-level optionality from value-level
undefined. - Choosing a specialized combinator vs. a more generic abstraction.
- Preserving existing semantics in a minor release while introducing a new helper.
2. Type Modeling Patterns
- How were inference, narrowing, or overloads preserved?
- What TypeScript limitation mattered?
- What exact type shape or helper solved it?
Project-relevant examples:
- Modeling
structschemas with required vs. optional keys. - Normalizing intersection-heavy inferred types for
tsd. - Preserving literal narrowing without assertion casts.
3. Runtime Validation Patterns
- What runtime behavior needed to match the type-level contract?
- What edge cases mattered?
- What implementation detail should future changes preserve?
Project-relevant examples:
- Own-key checks vs. inherited property checks in
struct. - Exact-mode semantics when optional keys are present or absent.
- Composing schema markers with existing value guards.
What ships with it
9 files 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.
- LEARNED_INDEX.md 1.8 KB
- learned/deprecate-public-api-before-major-removal.md 2.7 KB
- learned/keep-typed-schema-key-coverage-explicit.md 3.7 KB
- learned/model-transformations-as-decoders.md 3.1 KB
- learned/order-precise-overloads-before-generic-fallbacks.md 2.7 KB
- learned/preserve-explicit-generic-call-compatibility.md 2.6 KB
- learned/require-singleton-keys-for-single-property-refinements.md 3.9 KB
- learned/separate-property-refinement-absence-contracts.md 3.9 KB
- learned/test-packed-artifacts-from-a-consumer-project.md 2.7 KB
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.
- yesterday First seen · 152 lines · 38 tokens per session scan A db362ac51fc4
learn is a skill published in the GitHub repository nyaomaru/is-kit (71 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 976 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 2026-09-01.
Other skills, from other repositories
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
obsidian-markdown
Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.
wiki-lint
Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…
new-changelog
Create the next desktop changelog entry when asked to add a changelog file or prepare the next release note under packages/changelog/content. Use this when the task is specifically about determining the next version and creating the markdown entry.
predictor-hand-skill
Expert knowledge for AI forecasting — superforecasting principles, signal taxonomy, confidence calibration, reasoning chains, and accuracy tracking.
getting-started
Get started with your Open SaaS project — fetches docs, checks Wasp installation, and helps you start your database and app.