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/sdcorejs/sdcorejs-agent/sdcorejs-documentationnpx skills add sdcorejs/sdcorejs-agent --skill sdcorejs-documentationgit clone --depth 1 https://github.com/sdcorejs/sdcorejs-agentWhat 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 | $0.00104 | $0.03036 |
| Opus 5 | $0.00052 | $0.01518 |
| Sonnet 5 | $0.00021 | $0.00607 |
| Haiku 4.5 | $0.00010 | $0.00304 |
Grade A, and why
sdcorejs-documentation 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.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation
Shared Protocols
Read _refs/shared/runtime-protocols.md; load
_refs/shared/documentation-layout.md only for operations below
.sdcorejs/documentation/**. Every .sdcorejs/** write applies
_refs/shared/artifact-lifecycle.md and emits artifact_context. Resolve
tracks through _refs/shared/system-registry.json, approved artifact identity
through _refs/shared/approved-artifact.mjs, and semantic repository ownership
through _refs/shared/repository-contract.mjs; checkout paths and the current
working directory are never durable repository identity.
Purpose
Expose one documentation skill while keeping detailed documentation behaviors in
refs. This skill chooses the mode, loads the matching _refs/documentation/*
reference, then executes it.
Long-term documentation verbs owned here:
- write
- rewrite
- improve
- structure
- summarize existing docs/artifacts
- convert
- standardize
Core Documentation Modes
Keep documentation modes distinct. Do not mix them unless the user explicitly asks for multiple outputs.
| Mode | Purpose | Primary reader | Output |
|---|---|---|---|
code-documentation |
Document source code with public contracts and/or implementation comments. | Developer using or maintaining the code. | Python docstrings, JSDoc/TSDoc, conventional doc comments, inline/block implementation comments. |
write-user-guide |
Explain how an end user, admin, or operator performs a task. | Non-developer user, admin, support, operator. | Task-oriented Markdown guide. |
write-technical-doc |
Explain system design, API behavior, integration, setup, or maintenance. | Developer, tech lead, maintainer, or API consumer. | Developer-facing Markdown documentation. |
api-doc is a subtype of write-technical-doc, not a separate skill mode.
Global Documentation Rules
- Choose the documentation mode from user intent and source evidence.
- Do not mix documentation modes unless the user explicitly asks.
- Do not invent behavior, architecture, workflows, API fields, commands, roles, screens, infrastructure, or business rules that are not visible from code, tests, configuration, decorators, filenames, existing docs, type annotations, or surrounding context.
- Prefer concise, accurate, maintainable documentation over verbose documentation.
- Match the project's existing tone, terminology, formatting, and documentation style.
- Preserve executable code unless the user explicitly asks for code changes.
- Do not rename symbols, reorder decorators, or change imports unless a documentation tool explicitly requires it and the user asked for that tool.
- Update stale or wrong existing documentation instead of adding duplicate or contradictory content.
- Keep code identifiers, commands, environment variables, config keys, API paths, UI labels, class names, method names, and file names exact.
- Runtime-localize generated prose; keep reusable skill source English-only.
- Never include real secrets, tokens, passwords, private keys, production
credentials, or sensitive internal values. Use placeholders such as
<API_KEY>,<PROJECT_ID>,<USER_ID>, orexample.com. - Mark destructive or irreversible actions clearly.
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 · 227 lines · 104 tokens per session scan A 0f10f7c4a03b
sdcorejs-documentation is a skill published in the GitHub repository sdcorejs/sdcorejs-agent (2 stars, last pushed 15d ago), licensed MIT. It adds 104 tokens to every session and 3,036 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…