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 skills add elct9620/ai-spec-skills --skill spec-frameworkgit clone --depth 1 https://github.com/elct9620/ai-spec-skillsWrote 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/elct9620/ai-spec-skills/spec-framework)<a href="https://agentmods.dev/skills/elct9620/ai-spec-skills/spec-framework"><img src="https://agentmods.dev/badge/skills/elct9620/ai-spec-skills/spec-framework/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/elct9620/ai-spec-skills/spec-framework"><img src="https://agentmods.dev/badge/skills/elct9620/ai-spec-skills/spec-framework.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00036 | $0.01436 |
| Opus 5 | $0.00018 | $0.00718 |
| Sonnet 5 | $0.00007 | $0.00287 |
| Haiku 4.5 | $0.00004 | $0.00144 |
Grade A, and why
spec-framework 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 9d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specification Framework
Detailed structure for each layer of a specification.
Applicability Rubric
| Condition | Pass | Fail |
|---|---|---|
| Structuring new spec | Writing a spec from scratch | Spec structure already established |
| Layer completeness check | Need to verify all layers are addressed | Layers are already complete |
| Element selection | Deciding which elements to include | Elements already chosen |
| Multi-layer coordination | Ensuring layers align with each other | Single-layer change only |
Apply when: Any condition passes
Core Principles
Intent Layer
Provides context for judgment calls:
| Element | Role | Core |
|---|---|---|
| Purpose | What problem the system solves | ✓ |
| Users | Who uses it, what they accomplish | ✓ |
| Impacts | What behavior changes indicate success (drives priority) | |
| Success criteria | What defines "done" and "working" | |
| Non-goals | What the system deliberately is not; building it contradicts Purpose or Users | |
| Out of Scope | What this specification does not cover, though it is compatible with intent |
Without intent, implementers make technically correct but misaligned decisions.
Non-goals vs Out of Scope: Both describe things that will not be built now, but they instruct the reader differently—a Non-goal tells a contributor to stop, an Out of Scope item tells them to seek a scope decision. Keep them as separate sections so the section heading itself carries the instruction; a category column inside one list gets skimmed past. Each Out of Scope entry states the boundary the target state holds instead; a tracking reference may follow it when the target is confirmed to exist, and never a timeline. See spec-principles Scope Exclusions for the discriminator test.
## Non-goals
Building these would contradict what this system is:
- No web UI — this tool composes into shell pipelines
## Out of Scope
Compatible with intent; this specification does not cover them:
- Multi-language UI — every message ships in one language and is never resolved per locale
- Batch import — creation accepts one record per request; see ROADMAP.md#import
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.
- 9d ago First seen · 155 lines · 36 tokens per session scan A 2517d9395988
spec-framework is a skill published in the GitHub repository elct9620/ai-spec-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,436 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…