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-consolidatenpx skills add schmidthole/serf --skill spec-consolidategit clone --depth 1 https://github.com/schmidthole/serfWrote 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/schmidthole/serf/spec-consolidate)<a href="https://agentmods.dev/skills/schmidthole/serf/spec-consolidate"><img src="https://agentmods.dev/badge/skills/schmidthole/serf/spec-consolidate.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 5.1 | $0.00033 | $0.01516 |
| Opus 5 | $0.00016 | $0.00758 |
| Sonnet 5 | $0.00007 | $0.00303 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
spec-consolidate 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 5d 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 — 140 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
analyze the project's feature specs for fragmentation, overlap, and drift from the actual codebase, then consolidate them into unified features that accurately represent the product. $ARGUMENTS is an optional feature name to scope the analysis to a single feature and its related specs. if omitted, analyze all features.
/spec-consolidate
/spec-consolidate configuration
follow these steps:
analysis
-
read all features. read
specs/features/features.mdand then read every feature'sproposal.mdandspec.md. build a mental map of:- each feature's purpose and scope
- each feature's source paths
- each feature's status
-
read the codebase. for every source path referenced across all features, verify the path exists and read enough of the code to understand what it implements. also look for source files that are not referenced by any feature.
-
read archived work items. glob for
specs/work/archive/*.mdand read their frontmatter and summaries. this reveals how features evolved over time and which work items amended existing features versus building new ones. -
identify consolidation candidates. look for these patterns:
- overlapping source paths: two or more features listing the same source paths or directories. this usually means one feature was created to amend another but was written as a separate feature instead.
- subset features: a feature whose entire scope is a subset of another feature's scope (e.g. "config-hot-reload" is really part of "configuration").
- split features: a single logical capability that was split across multiple feature directories (e.g. "auth-login" and "auth-session" that should be one "authentication" feature).
- superseded features: a newer feature that replaces an older one without the older one being updated or removed.
- orphaned features: features with status
implementedwhose source paths no longer exist, or features that no longer correspond to anything in the codebase.
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.
- 5d ago First seen · 140 lines · 33 tokens per session scan A 9f7fdaf6c269
spec-consolidate is a skill published in the GitHub repository schmidthole/serf (2 stars, last pushed 5mo ago), licensed BSD-3-Clause. It adds 33 tokens to every session and 1,516 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…