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/asteasolutions/ai-toolkit/to-specnpx skills add asteasolutions/ai-toolkit --skill to-specgit clone --depth 1 https://github.com/asteasolutions/ai-toolkitWrote 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/asteasolutions/ai-toolkit/to-spec)<a href="https://agentmods.dev/skills/asteasolutions/ai-toolkit/to-spec"><img src="https://agentmods.dev/badge/skills/asteasolutions/ai-toolkit/to-spec.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 | $0.00051 | $0.00562 |
| Opus 5 | $0.00026 | $0.00281 |
| Sonnet 5 | $0.00010 | $0.00112 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
to-spec 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
to-spec
Turn settled conversation into a thin Plan. Do not interview — grilling already happened; capture what was decided.
Shapes match helm's work-tree artifacts (see helm/references/artifacts.md if present).
Publish policy
- Always write local under
.scratch/<goal-slug>/— this is the program counter. - Also mirror to GitHub only when the user asks for GitHub, or already pointed at an issue URL/id. If
docs/agents/issue-tracker.mdexists, follow its GitHub conventions for that mirror. - Never skip the local write. Never ask which tracker after a local-only run.
Process
-
Orient if needed. If the touched area isn't already understood, explore it. Prefer any domain vocabulary / decision docs the repo already has; discover them — don't invent a layout.
-
Sketch test seams. Prefer existing seams; pick the highest seam that still exercises the behaviour; minimise their number (ideal: one). Check seams with the developer before writing.
-
Write a thin Plan into the leaf doc:
- Undecomposed goal:
.scratch/<goal-slug>/task.md - If Intent already exists (helm Capture), fill or replace only the
## Plansection. - If starting fresh, write Intent (short what+why) + Plan.
Thin Plan contents only:
- what / why
- test seams (how it will be verified)
- implementation decisions
- behaviour-level
donecriteria
No brittle file paths or code. Exception: a decision-encoding prototype (schema, type, state machine) may be inlined when the shape is the decision.
- Undecomposed goal:
-
Ask once about extras. After the thin Plan is written, ask whether to also include any of: user stories, out of scope, further notes (or other sections the developer names). Default is no. Add only what they pick.
-
GitHub mirror (opt-in). If publishing to GitHub, create/update the issue from the same Plan body. Local remains source of truth for resume.
Leaf shape
# <feature title>
## Intent
<what + why>
## Plan
<what/why · test seams · implementation decisions · behaviour-level done criteria>
<!-- optional extras only if the developer asked for them -->
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 53 lines · 51 tokens per session scan A 4f00ca8a1c0e
to-spec is a skill published in the GitHub repository asteasolutions/ai-toolkit (5 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 562 once invoked, about $0.0003 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-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…
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…