A validator for a world model: a structured collection of entities, links, rules, and related information. It checks both individual records and relationships across files.

Use it to lint the model, report health measures and anti-patterns, and block pushes when serious defects are found.

It finds malformed data, broken links, duplicate identifiers, stale connections, and visibility mistakes before changes are pushed.

lw-lint — Skill for Claude Code by matteoroversi

Install

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.

Any agent

npx skills add matteoroversi/lookward --skill lw-lint

Clone the repo

git clone --depth 1 https://github.com/matteoroversi/lookward

Made for: Claude Code.

Or install lookward, the plugin that ships this one along with the rest of its 5 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/matteoroversi/lookward/lw-lint/github.svg)](https://agentmods.dev/skills/matteoroversi/lookward/lw-lint)

Your own site

<a href="https://agentmods.dev/skills/matteoroversi/lookward/lw-lint"><img src="https://agentmods.dev/badge/skills/matteoroversi/lookward/lw-lint/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/matteoroversi/lookward/lw-lint"><img src="https://agentmods.dev/badge/skills/matteoroversi/lookward/lw-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,190 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00064	$0.01190
Opus 5	$0.00032	$0.00595
Sonnet 5	$0.00013	$0.00238
Haiku 4.5	$0.00006	$0.00119

Measured 12d ago against content hash aa790792db95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lw-lint 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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (lint.py, test_lint.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/lw-lint/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

lw-lint

Validate the world model. Mechanical and quiet (not a conversational skill). Loads ontology/contract.md. Runs lint.py for the deterministic frontmatter/schema checks; reasons over the report for the heavier multi-file ones. Every defect caught by hand becomes a new rule here — the rule set grows from real failures, not imagined risks.

Severity = the gate model (from the contract): blocker/major are Violation — they gate the push (exit 2/1); minor is Warning/Info — a proposal that does not gate (exit 0). The human approves the proposals; only Violations block.

Two tiers, honestly scoped:

Enforced by lint.py today — per-node frontmatter (required keys incl. lookward.world_model/visibility, id present & a stable slug-or-ULID, type validity vs seed/special/promoted, purpose, and the provenance/visibility/face/confidence enums), status lifecycle + tombstone integrity (deprecated → replaced_by), connector freshness (last_synced), boundary keys incl. mandatory lookward.statement + the kind/strength/enforcer enums, the will-chain on the lookward.root node, exactly-one-root, duplicate-id (a blocker), root-exists / non-empty, the spine-gate (a node of a promoted type requires ontology.md to exist and declare that type — the static proxy for "spine before nodes"), and ontology.md version (anchored to a version: key or vN.N, not any bare decimal).
Reasoned by the skill (not deterministic) — links/orphans, citation invariant, the Kitchen-Sink mirror check (object types must model real-world concepts, not copy a source's columns 1:1 — a modeling judgement, not a static one), the kinetic action-contract validity (each action in ontology.md carries parameters/rules/submission_criteria/side_effects/execution; rules from the closed catalog; execution: auto only on read-only verbs), identifier-reuse, God-Object accretion, health metrics, rebuildability.
Planned, NOT yet enforced (post-v0) — the visibility/audience push gate, the block-level projection leak-check, typed-relation target resolution (the relations: list-of-objects schema), and datasource: validation. These depend on the projection generator / a richer parser, which v0 does not build. Do not rely on them as enforced until shipped.

Read the full file on GitHub · 45 lines

Files

What ships with it

2 files 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.

Changes

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.

12d ago First seen · 45 lines · 64 tokens per session scan A aa790792db95

Subscribe to this mod's changes

lw-lint is a skill published in the GitHub repository matteoroversi/lookward (7 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,190 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

lw-lint

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

lw-lint

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

research-engineer

tika-eval-compare

neuron-evaluation-engineer

jetson-validate-image

atmos-validation

skill-benchmark