screenshot-sync

screenshot-sync is a skill for Claude Code, Codex from Generous-Corp/pulp. It costs 167 tokens per session (5,319 once invoked), scanned A, original, MIT.

A workflow for keeping project screenshots, web preview images, and gallery thumbnails matched to the current user interface.

In plain words
What is it for?
It helps recapture and update every opted-in screenshot use after a user-interface change, with a check that can stop a pull request when one is missing.
Why use it?
Interface changes can leave documentation and preview images showing an old design, and forgotten images may otherwise pass unnoticed.

Skill for Claude CodeCodex

Part of the pulp plugin — 63 skills, 30 commands, 3 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/generous-corp/pulp/screenshot-sync
Any agent
npx skills add Generous-Corp/pulp --skill screenshot-sync
Clone the repo
git clone --depth 1 https://github.com/Generous-Corp/pulp

Made for: Claude Code, Codex.

Or install pulp, the plugin that ships this one along with the rest of its 63 skills, 30 commands, 3 hooks, 1 MCP server.

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.

agentmods badge for screenshot-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/generous-corp/pulp/screenshot-sync.svg)](https://agentmods.dev/skills/generous-corp/pulp/screenshot-sync)
Your own site
<a href="https://agentmods.dev/skills/generous-corp/pulp/screenshot-sync"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/screenshot-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 167 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00167 $0.05319
Opus 5 $0.00084 $0.02660
Sonnet 5 $0.00033 $0.01064
Haiku 4.5 $0.00017 $0.00532

Measured today against content hash 7d34a52de1fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

screenshot-sync scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

redeploy; verify with `curl -s <preview>/…/ | grep og:image`. Production needs no override
.agents/skills/screenshot-sync/SKILL.md · 361 lines

How it starts

The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.

screenshot-sync

Keep a repo's screenshots in lockstep with its UI. When the UX changes, the README shot, the web-demo Open Graph preview (og.png), and the gallery thumbnail all have to change with it — this skill re-captures them and the screenshot_sync_check.py gate fails a PR that forgot to.

Read the screenshot skill first for the raw capture mechanics (backends, the image-compositing trap, the content-floor oracle, vision-probe). This skill is the sync/consume orchestration on top of it.

When this applies

  • A repo carrying .pulp/screenshots.toml had a UX-path change and the screenshot-sync gate (pre-push / CI) or PostToolUse hint fired, OR
  • "update the screenshots / OG images / gallery thumbs", "backfill the WCLAP OG images", "the demo preview image is stale / links don't unfurl".

0. Confirm opt-in

Screenshots are a plugin-with-releases concern, not a core/tooling one. Check for .pulp/screenshots.toml at the repo root. Absent → the repo is not opted in; stop. Do not invent screenshots for a library/tool/core repo. Opt-in is per-repo by the file's presence — the same pattern ~/.config/pulp/daw-smoke.toml and .shipyard.local/config.toml use.

Default opt-in set: the packaged-demo and packaged-examples consumers (gpu-nam, bendr, superconvolver, spectral-lab, tempo-sampler, classic-effects, pulp-example-plugins). Everything else — pulp core included — stays off.

The manifest: .pulp/screenshots.toml

One file per opted-in repo, at its root. It lists the UX paths that should trigger a re-shoot and, for each screenshot target, its capture route and every place the image is consumed — so one re-shoot fans out to README + OG

  • gallery and they cannot drift.
schema_version = 1

# UX paths whose change should trigger a re-shoot (repo-relative, gitignore-style
# globs — the same dialect skill_path_map.json uses). A design-token change
# reskins every widget, so a trigger hit invalidates ALL targets in the repo.
[trigger]
paths = [
  "src/**/*_editor.cpp",
  "ui/**/*.js",
  "assets/design-system/**/*.css",
  "assets/design-system/**/*.tokens.json",
]

# ── Native README / editor shot (capture route A) ──
[[target]]
id      = "mono-synth-editor"
route   = "native"                 # render_to_png / pulp-screenshot, Skia/gpu
tool    = "pulp-mono-synth-shot"   # per-editor dumper target (brew_shots.cpp pattern)
size    = "720x460"
scale   = 2.0                      # match the native editor baseline (test_editors.cpp)
backend = "skia"                   # or "gpu" for requires_gpu_host() views
consumes = [
  { kind = "readme", path = "docs/img/mono-synth.png" },
]

# ── Web demo OG + gallery (capture route B) ──
[[target]]
id                  = "mono-synth-web"
route               = "web"
url                 = "example-plugins/mono-synth/index.html"
device_scale_factor = 2
consumes = [
  { kind = "og",      path = "example-plugins/mono-synth/og.png" },
  { kind = "gallery", path = "docs/gallery/mono-synth.png" },
  { kind = "og_meta", html = "example-plugins/mono-synth/index.html", rel = "./og.png" },
]

[[target]]
id                  = "example-gallery-web"
route               = "web"
url                 = "example-plugins/index.html"
device_scale_factor = 2
# A target may narrow the global trigger to just the paths that affect IT:
trigger = [ "ui/**/*.js", "assets/design-system/**" ]
consumes = [
  { kind = "og",      path = "example-plugins/og.png" },
  { kind = "og_meta", html = "example-plugins/index.html", rel = "./og.png" },
]

Read the full file on GitHub · 361 lines

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.

  1. today First seen · 361 lines · 167 tokens per session scan A 7d34a52de1fe

Subscribe to this mod's changes

screenshot-sync is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 167 tokens to every session and 5,319 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens