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/schmidthole/serf/spec-newnpx skills add schmidthole/serf --skill spec-newgit clone --depth 1 https://github.com/schmidthole/serfWhat 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 | $0.00024 | $0.01000 |
| Opus 5 | $0.00012 | $0.00500 |
| Sonnet 5 | $0.00005 | $0.00200 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
spec-new 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reference
read development-workflow.md for the full conventions governing the specs directory structure, features, work items, and their formats.
instructions
scaffold a new feature directory and draft its proposal and spec based on the provided description. expects $ARGUMENTS in the format:
/spec-new <feature-name> <description of the feature>
the description can be as brief or detailed as the user wants. use whatever context is provided to draft meaningful content for the proposal and spec files.
follow these steps:
-
validate the name. the feature name should be lowercase kebab-case. if it contains spaces or uppercase letters, convert it.
-
check for duplicates. glob for
specs/features/<feature-name>/. if it already exists, inform the user. -
understand the codebase. read the project's
README.mdand any existing features inspecs/features/features.mdto understand the project context. this informs how the new feature fits into the existing architecture. -
check for overlap with existing features. for each existing feature listed in
features.md, read itsproposal.mdandspec.md. compare the new feature's described purpose, use cases, and likely source paths against existing features. look for:- the new feature's functionality is a subset of an existing feature
- the new feature would share source paths with an existing feature
- the new feature extends or modifies behavior already covered by an existing feature
- the new feature's name or description is closely related to an existing feature
if overlap is detected, inform the user with specifics:
- which existing feature(s) overlap
- what the overlap is (shared scope, shared source paths, extension of existing behavior)
- a recommendation: would this be better as an amendment to the existing feature via
/spec-amend?
ask the user to choose:
- continue as new feature: proceed with creating a standalone feature (the user may have good reasons for separation)
- convert to amendment: stop the
/spec-newflow and inform the user to run/spec-amend <existing-feature> <description>instead
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 · 106 lines · 24 tokens per session scan A b8c6aef24e00
spec-new is a skill published in the GitHub repository schmidthole/serf (2 stars, last pushed 5mo ago), licensed BSD-3-Clause. It adds 24 tokens to every session and 1,000 once invoked, about $0.0001 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…