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-initnpx skills add schmidthole/serf --skill spec-initgit 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 | $0.00030 | $0.00892 |
| Opus 5 | $0.00015 | $0.00446 |
| Sonnet 5 | $0.00006 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
spec-init 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 — 77 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
initialize or align a specs directory with the spec-driven development structure defined in the development workflow. $ARGUMENTS is an optional path to a specific service directory in a monorepo (e.g. /spec-init services/auth). if omitted, targets the repo root.
follow these steps:
-
determine the target root. if
$ARGUMENTSprovides a path, use it. otherwise use the repository root. -
check for an existing specs directory. glob for
<target>/specs/. if it exists, switch to alignment mode. if not, switch to scaffold mode.
scaffold mode (no existing specs directory)
-
create the directory structure:
<target>/specs/features/<target>/specs/work/active/<target>/specs/work/archive/
-
create
specs/features/features.mdwith this template:
# Features
| Feature | Description |
|---|---|
- confirm creation by listing all directories and files created.
alignment mode (existing specs directory)
-
audit the current structure. check for the presence of:
specs/features/directoryspecs/features/features.mdindexspecs/work/active/directoryspecs/work/archive/directory
-
create any missing directories or files using the same templates as scaffold mode.
-
audit existing features. glob for all subdirectories under
specs/features/. for each:- check if it has a
proposal.md— if missing, note it - check if
proposal.mdhasstatusfrontmatter — if missing, note it - check if it has a
spec.md— if missing, note it - check if it has a
## Source Pathssection inspec.md— if missing, note it - check if it has an
amendments/directory — not required, but note any amendment files found for context - if
proposal.mdhasstatus: consolidated, check thatconsolidated_intois present and references a valid feature - check if the feature is listed in
features.md— if missing, note it (consolidated/retired features should not be in the index)
- check if it has a
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 · 77 lines · 30 tokens per session scan A 7c537e04081f
spec-init is a skill published in the GitHub repository schmidthole/serf (2 stars, last pushed 5mo ago), licensed BSD-3-Clause. It adds 30 tokens to every session and 892 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…