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/nearform/lastlight/docs-syncnpx skills add nearform/lastlight --skill docs-syncgit clone --depth 1 https://github.com/nearform/lastlightWhat 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 | $0.00106 | $0.02602 |
| Opus 5 | $0.00053 | $0.01301 |
| Sonnet 5 | $0.00021 | $0.00520 |
| Haiku 4.5 | $0.00011 | $0.00260 |
Grade A, and why
docs-sync 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 yesterday.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-sync
Last Light's documentation lives in two surfaces, and a code change can
silently invalidate either. Since the monorepo migration both live in this
repo (nearform/lastlight) — the www site is no longer a separate repo, so a
doc update lands in the same commit as the code change:
- In-repo spec —
apps/server/spec/*.md. This is the rebuild-grade contract. It is the source of truth for the website's/spec/section:apps/www/scripts/sync-spec.mjscopies these files intoapps/www/src/content/spec/at build time. So editingapps/server/spec/*.mdis how you update the public spec — no separate edit underapps/wwwis needed for spec pages. - Hand-written site —
apps/www/src/pages/docs/*.astro,apps/www/src/pages/*.astro,apps/www/src/data/docs-nav.ts,apps/www/src/pages/llms.txt.ts. These are not generated from anything. They drift the most. - The homepage —
apps/www/src/pages/index.astro. Called out separately because it is the page nobody remembers to update and the one every visitor reads first. It makes countable, falsifiable claims (how many dashboard tabs, which sandbox backends, which skills exist) that go stale silently: an August 2026 audit found it still claiming "four tabs" against eleven, and two sandbox backends against five. It is marketing copy, so it does not list everything — but nothing on it may be wrong, and a genuinely new user-facing capability belongs there. Same rule for/comparisons/*, whose "what Last Light does that X doesn't" lists are claims about us.
The recurring failure mode: a workflow or skill is added and neither surface is updated. This skill exists to close that gap.
Counts are the tell. Any doc sentence containing a number that enumerates code ("four tabs", "two backends", "eleven workflows") is a liability. When you touch the thing being counted, grep the docs for the count and fix it — or better, reword it so it does not need a number.
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.
- yesterday First seen · 145 lines · 106 tokens per session scan A e40269fe414f
docs-sync is a skill published in the GitHub repository nearform/lastlight (22 stars, last pushed 4d ago), licensed MIT. It adds 106 tokens to every session and 2,602 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
example-skill
Counts lines, words, and bytes in a text file using the bundled count.sh script. Use when asked to count/measure a file's size in these terms.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
gpt-taste
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.