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-skill-authoringnpx skills add sdcorejs/sdcorejs-agent --skill sdcorejs-skill-authoringgit clone --depth 1 https://github.com/sdcorejs/sdcorejs-agentWrote 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/sdcorejs/sdcorejs-agent/sdcorejs-skill-authoring)<a href="https://agentmods.dev/skills/sdcorejs/sdcorejs-agent/sdcorejs-skill-authoring"><img src="https://agentmods.dev/badge/skills/sdcorejs/sdcorejs-agent/sdcorejs-skill-authoring.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00050 | $0.01368 |
| Opus 5 | $0.00025 | $0.00684 |
| Sonnet 5 | $0.00010 | $0.00274 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
sdcorejs-skill-authoring 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 4d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDCoreJS Skill Authoring
Author skill-pack changes from behavioral evidence, not from plausible-looking Markdown. This capability owns authoring discipline only; existing public skills retain their product, implementation, review, repair, and ship owners.
Scope boundary
- Apply only while authoring the
sdcorejs-agentrepository or this skill pack. - Keep this capability under
authoring/, outside publicskills/**. - Never add it to harness manifests, generated mirrors, adapter inventories, the site catalog, package installation output, or target projects.
- Edit canonical public sources first. Generate public mirrors only with the repository sync command; never hand-copy a mirror.
- Do not treat a deadline, requester title, or batch request as approval to change dispatch contracts or inventory limits.
Read authoring/README.md, authoring/evals/scenarios.json, and
authoring/evals/skill-authoring-contract.mjs before making an authoring
decision.
New-skill decision gate
Default to an existing surface. A new public skill is justified only when all of these are evidenced:
- distinct user intent and trigger;
- distinct lifecycle;
- distinct artifact authority or execution boundary;
- no clean expression as an existing skill action, mode, or reference;
- positive and negative routing evidence;
- acceptable surface and complexity cost.
Otherwise choose exactly one owned fallback:
existing-skill-mode;shared-reference;executable-helper;test-fixture;documentation-only.
Call evaluateNewSkillDecision. It derives public names/count/hash and the
routing-matrix hash from this repository; supplied count or free-form routing
claims cannot replace them. Proposals are nonempty and cannot duplicate the
inventory. Adding a trigger needs a canonical approved artifact resolved from
the trusted loader and bound to actor, proposal scope, the current Git revision,
and current inventory hash. A colocated JSON file and its caller-computed hash
are not approval. The public count has ceiling 23;
a boolean or owner instruction cannot override it.
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.
- 4d ago First seen · 146 lines · 50 tokens per session scan A 58d1309fc224
sdcorejs-skill-authoring is a skill published in the GitHub repository sdcorejs/sdcorejs-agent (2 stars, last pushed 17d ago), licensed MIT. It adds 50 tokens to every session and 1,368 once invoked, about $0.0003 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…