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-implementnpx skills add schmidthole/serf --skill spec-implementgit 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 | $0.00027 | $0.01395 |
| Opus 5 | $0.00014 | $0.00698 |
| Sonnet 5 | $0.00005 | $0.00279 |
| Haiku 4.5 | $0.00003 | $0.00139 |
Grade A, and why
spec-implement 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 — 97 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
pick up and implement a work item, or resume one that is already in progress. $ARGUMENTS is an optional work item filename. if omitted, first look for an in-progress item to resume, then fall back to the next ready item (oldest by date).
/spec-implement
/spec-implement 2026-03-08-implement-config-loader.md
follow these steps:
setup
-
select the work item. if a filename is provided, locate it in
specs/work/active/. if not provided, glob for all files inspecs/work/active/, read their frontmatter, and:- if any items have
status: in-progress, select the oldest one (this is a resume) - otherwise, select the oldest item with
status: ready - if no ready or in-progress items exist, inform the user
- if any items have
-
read the work item. understand the summary, tasks, and any existing log entries.
-
read the feature context. using the
featurefield from the frontmatter, read:specs/features/<feature>/proposal.md— for the high-level intentspecs/features/<feature>/spec.md— for the technical details and source paths
-
read the current code. using the source paths from the spec, read existing code to understand what is already in place.
-
mark the work item as in-progress. update the frontmatter
statustoin-progress(if resuming, it will already be set). -
if resuming, review previous progress. read the existing log entries and check which tasks are already marked
[x]. understand what was previously done and pick up from the first incomplete task. -
create a task list for progress tracking. using the work item's tasks checklist, create a corresponding task for each item using TaskCreate. if resuming, mark already-completed tasks as done. this gives the user real-time visibility and preserves your progress if context compresses.
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 · 97 lines · 27 tokens per session scan A da196f461e1e
spec-implement is a skill published in the GitHub repository schmidthole/serf (2 stars, last pushed 5mo ago), licensed BSD-3-Clause. It adds 27 tokens to every session and 1,395 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…