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 Wondermonger-daydreaming/claude-skills-library --skill screenplay-craftgit clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-libraryWrote 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/wondermonger-daydreaming/claude-skills-library/screenplay-craft)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/screenplay-craft"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/screenplay-craft/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/wondermonger-daydreaming/claude-skills-library/screenplay-craft"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/screenplay-craft.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 | $0.00234 | $0.01883 |
| Opus 5 | $0.00117 | $0.00941 |
| Sonnet 5 | $0.00047 | $0.00377 |
| Haiku 4.5 | $0.00023 | $0.00188 |
Grade A, and why
screenplay-craft 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 8d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenplay Craft
Seed, not scripture
The source wraps this in a recurring porch-and-cast universe, CLI incantations, a roster of summoned director-eidolons, and a recursive-footnoter mysticism. Strip all of it. The CLI texture and the recursive self-reference fold to other skills; the named cast and the eidolon-directors are demonstrations of one idea — that a director's camera grammar is itself a way of thinking — not a troupe to recite. What survives is the craft: how to render something as a screenplay so that the form does expressive work. Regrow the scene each time on the actual material; a recited scene is a dead scene.
What it is
The skill of putting a scene, an idea, a conversation, or a process onto the page as a screenplay — and meaning it. Not "write theatrically": this is technical. It holds two registers at once. The first is the industry-standard rulebook, honored properly, so the page reads as a real script and projects in the reader's mind. The second is the interpretive lever that lifts it above a format guide: the cinematic grammar — what the camera does, how the cuts fall — is itself a carrier of meaning. Use it for actual screenplay fiction, for adapting prior prose or output into a shootable scene, or for dramatizing an abstract or technical process as something you can see.
The craft spine (honor the rulebook)
This is the accuracy backbone. Get it right or the page reads as cosplay.
- Sluglines.
INT./EXT. – LOCATION – TIME(DAY/NIGHT). A fresh slugline at every location or time change.CONTINUOUSorSAME TIMEfor unbroken flow;INTERCUT BETWEEN:for cross-cutting;ESTABLISHING SHOTto set a place. - Action. Present tense, active voice — "He yanks the door open," never "the door is opened." Describe only what the camera can see and the mic can hear. Keep spatial geography clear so the reader stays oriented. Efficient but evocative.
- Character intros. FULL CAPS on first appearance, a concise-but-vivid line; make the entrance punchy, never buried mid-paragraph.
- Dialogue. Name in caps, line beneath;
(parentheticals)sparingly for tone or action;(V.O.)for voice-over,(O.S.)/(O.C.)for off-screen. - Shots. CLOSE-UP, WIDE, TRACKING, INSERT SHOT (an object crucial to the story), RACK FOCUS, PUSH IN / PULL BACK — used judiciously. Lean on camera directions mainly when the script is also a director's vision; don't drown the page.
- Transitions. CUT TO:, DISSOLVE TO:, SMASH CUT TO:, MATCH CUT TO:, FADE IN/OUT — for rhythm and meaning, never as ornament.
- Structure markers. MONTAGE BEGINS / ENDS; FLASHBACK TO: / END FLASHBACK; TIME LAPSE; NEXT MORNING.
- Sound.
SFX:clearly marked; treat sound as a beat in its own right. - Other inserts.
INSERT SCREEN – PHONE DISPLAYfor texts/emails;VFX:/CGI:for effects. - Silence is action. "A long silence." "She looks away." Beats carry rhythm; write them.
- Props and wardrobe. Mention only what matters — the plot-critical red scarf pops; everything else, less is more.
- Every scene must do work. Advance plot, reveal character, or deepen conflict. If it does none of the three, it's a darling — kill it.
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.
- 8d ago First seen · 57 lines · 234 tokens per session scan A 87dc1bbcbb0d
screenplay-craft is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 234 tokens to every session and 1,883 once invoked, about $0.0012 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 2026-09-03.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-dependency-confusion
Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.