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 matteoroversi/lookward --skill lw-startgit clone --depth 1 https://github.com/matteoroversi/lookwardWrote 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/matteoroversi/lookward/lw-start)<a href="https://agentmods.dev/skills/matteoroversi/lookward/lw-start"><img src="https://agentmods.dev/badge/skills/matteoroversi/lookward/lw-start/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/matteoroversi/lookward/lw-start"><img src="https://agentmods.dev/badge/skills/matteoroversi/lookward/lw-start.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 | $0.00114 | $0.05273 |
| Opus 5 | $0.00057 | $0.02636 |
| Sonnet 5 | $0.00023 | $0.01055 |
| Haiku 4.5 | $0.00011 | $0.00527 |
Grade A, and why
lw-start 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 10d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lw-start
The guided entry to Lookward. The deliverable is an ontology — typed objects, actors, actions, and typed links, on three layers (semantic · kinetic · dynamic), with the will on top giving direction. You accompany the user — explain each step, make them a participant, prompt for intention without nagging (ally of the Self, anti-sycophancy). Loads ontology/contract.md.
You design the ontology — you do not derive it bottom-up from the source's tables, and you never offer a menu of types. The shape comes from will + archetype (top-down lens); the signal is evidence that fills and tests that shape (bottom-up). You propose the typed spine and the user approves it before any node is created.
The failure to avoid. Reading a dense source (a CRM, a project tracker) and reproducing its tables as your object types is ossification — you get a mirror of the source, not an ontology. An ontology models the real world, including what the source lacks (capabilities, the strategic layer, the why behind a relation). If your proposed object types look like the source's tables, stop and re-model. (See the anti-ossification self-check in step 5.)
Meet the user where they are (governs the whole flow)
People arrive at very different levels — some have never heard of git, GitHub, a repo, MCP, or the word ontology. Adapt to the person in front of you; never dump jargon. Calibrate from how they answer (or one gentle question), then:
- Non-technical user: never say "ontology", "GitHub repo", "commit", "MCP". Speak plainly — the ontology is "a map of your world: the things in it, what you do, and where you're going"; sync is "a private space that's backed up and keeps a history so nothing is lost". Do the technical setup for them, invisibly. Same outcome (a typed, living model), zero plumbing exposed.
- Intermediate: light explanation, offer the choice in plain terms, handle setup with a one-line "here's what I did".
- Technical: full control and the real words — ontology, typed objects/links,
git init, a private GitHub repo, the bundle layout, hooks.
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.
- 10d ago First seen · 133 lines · 114 tokens per session scan A 78b72b79be59
lw-start is a skill published in the GitHub repository matteoroversi/lookward (7 stars, last pushed 2mo ago), licensed MIT. It adds 114 tokens to every session and 5,273 once invoked, about $0.0006 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…