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-enrichgit 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-enrich)<a href="https://agentmods.dev/skills/matteoroversi/lookward/lw-enrich"><img src="https://agentmods.dev/badge/skills/matteoroversi/lookward/lw-enrich/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-enrich"><img src="https://agentmods.dev/badge/skills/matteoroversi/lookward/lw-enrich.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 | $0.00101 | $0.01423 |
| Opus 5.5 | $0.00040 | $0.00569 |
| Sonnet 5.5 | $0.00020 | $0.00285 |
| Haiku 4.5 | $0.00010 | $0.00142 |
Grade A, and why
lw-enrich 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 2mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lw-enrich
The living-loop step that turns signal into a richer model. Two jobs, one routine:
- Consolidate new captures in
sources/into proposed node edits. - Enrich the prose layer — the qualitative attributes no connector holds (the why, the rationale, the judgement, the relationship texture, the strategic reading). This is the moat (
foundations.md: two truths — structured comes from connectors, prose is hand-enriched here).
Proposes, never applies (Rule 2) — output is a diff/PR the human approves. Loads ontology/contract.md. Enrichment is a retrieval-quality lever, not cleanup.
What it does
-
Read the queue. New/changed captures in
sources/since the last run (watermark in.lookward/). Never re-process the whole corpus — time-windowed. Ifsources/holds no capture for an entity, you have no signal for it — stop and capture first (see "No signal, no node"). -
Entity resolution. Merge surface-form variants of the same real-world entity into one node
id; on merge, the loser's id becomes an alias so old links still resolve. One node = one real-world entity (anti-Kitchen-Sink). Divergent needs become typed subclasses, never forks (foundations.md: one name = one meaning). -
Propose spine changes back to
ontology.md— don't free-promote. A recurring new type label is a proposal to the typed spine (ontology.md), not a folder you silently create. The spine is owned by the modeling act (lw-startand its continuation);lw-enrichproposes the change there (with the[decision]rationale), so the ontology stays designed-from-will, never grown-by-accretion into a source mirror. On approval, the type is recorded in.lookward/promoted-types.txtand its folder created (named exactly the type, singular).- Grow the kinetic layer too, not only objects. When the signal shows a recurring verb the subject performs (a new way they act), propose it as a new action — the full typed-contract block (
parameters/rules/submission_criteria/side_effects/execution, percontract.md) inontology.md— not just a label. The kinetic layer must keep growing here, orlw-forgecan only ever agentify the actionslw-startwrote once.
- Grow the kinetic layer too, not only objects. When the signal shows a recurring verb the subject performs (a new way they act), propose it as a new action — the full typed-contract block (
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.
- 2mo ago First seen · 47 lines · 101 tokens per session scan A 58a8d98b7ffb
lw-enrich is a skill published in the GitHub repository matteoroversi/lookward (7 stars, last pushed 4mo ago), licensed MIT. It adds 101 tokens to every session and 1,423 once invoked, about $0.0004 per session on Opus 5.5. 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.
lw-enrich compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lw-enrichmatteoroversi/lookward | Skill | 7 | 4mo ago | MIT | A | 101 | Claude Code |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |