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/policyengine/policyengine-claude/policyengine-contentnpx skills add PolicyEngine/policyengine-claude --skill policyengine-contentgit clone --depth 1 https://github.com/PolicyEngine/policyengine-claudeWhat 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 | $0.00089 | $0.01069 |
| Opus 5 | $0.00044 | $0.00535 |
| Sonnet 5 | $0.00018 | $0.00214 |
| Haiku 4.5 | $0.00009 | $0.00107 |
Grade A, and why
policyengine-content 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 2d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PolicyEngine content generation
Turn a published post or announcement into shareable social assets: a 1200x630 image and platform copy. This skill supplies the template and the token/brand rules; the workflow itself runs through a command and agent.
Workflow entry
/generate-content(command) is the entry point. It takes asource(post URL or file),audiences(defaultuk,us), andoutputs(defaultall).- It dispatches the
content-orchestratoragent, which parses the source, generates localized variants, fills this skill's template, and renders each image by screenshotting the filled HTML in headless Chrome (--headless --screenshot --window-size=1200,630). - The
neutrality-revieweragent then checks the generated copy for advocacy, speculation, or one-sided framing before anything is published.
Do not hand-render assets when the command exists — invoke /generate-content and let the agents
own the mechanics. Follow the policyengine-writing skill for the copy's tone and neutrality.
The template (live)
templates/social-image.html in this skill dir is the live template the orchestrator fills and
screenshots. Keep it. It renders standalone in headless Chrome, so it carries literal hex values
(dark background #1a2332, teal accents) rather than importing a stylesheet — headless Chrome
does not resolve the app's CSS. Its {{placeholders}}:
headline_prefix, headline_highlight, subtext, badge, flags,
quote, attribution_name, attribution_title, headshot_url, logo_url
Notes that matter for Chrome-headless rendering: position the logo with top: not bottom:;
inline external images as data URIs (or download them locally first) so they load; always
preview the rendered PNG before using it.
Design tokens
The source of truth for color is @policyengine/ui-kit (theme.css), not any older package.
In app/chart/SVG contexts, import the theme and reference CSS variables — never hardcode hex:
@import "tailwindcss";
@import "@policyengine/ui-kit/theme.css";
/* then: var(--primary), var(--chart-1), var(--border), var(--color-gray-400) */
What ships with it
1 file 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.
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.
- 2d ago First seen · 93 lines · 89 tokens per session scan A 315b3eadfb29
policyengine-content is a skill published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed 8d ago), licensed MIT. It adds 89 tokens to every session and 1,069 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…