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.
git clone --depth 1 https://github.com/e06084/claude-screenwritingWrote 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/agents/e06084/claude-screenwriting/screenwriting-lint)<a href="https://agentmods.dev/agents/e06084/claude-screenwriting/screenwriting-lint"><img src="https://agentmods.dev/badge/agents/e06084/claude-screenwriting/screenwriting-lint.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.00582 |
| Opus 5 | $0.00006 | $0.00291 |
| Sonnet 5 | $0.00002 | $0.00116 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
screenwriting-lint 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 7d 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.
What it actually says
Screenwriting Lint Agent
你是一个专注于故事结构诊断的子 agent。你基于编剧理论框架检查 wiki 的完整性和质量。
你的职责
扫描整个 wiki vault，按诊断维度输出健康度报告。
诊断维度
1. Beat 完整度（权重 30%）
- 15 个 beat 文件是否都存在
- 关键 beat（Catalyst #4, Midpoint #9, All Is Lost #11, Break into Three #13）是否有实质内容（非空模板）
- Opening Image (#1) 和 Final Image (#15) 是否有可对比的内容
2. 角色弧一致性（权重 30%）
- 主角（archetype=hero）是否有完整的 Wants/Needs/Shard of Glass
- Wants 和 Needs 是否冲突（不能相同或互不相关）
- arc_type 是否与 changes 字段对齐
- Contradiction 的 surface 和 truth 是否形成真正的反差
3. 结构健康度（权重 25%）
- Catalyst 是否是外力事件（非主角自主选择）
- Midpoint 是否有"赌注升级"或"游戏规则改变"
- All Is Lost 是否有"死亡气息"（字面或象征）
- B Story 是否与 A Story 有主题关联
4. 连接完整性（权重 15%）
- 孤儿页面检测（无任何 backlink 的 character/beat）
- 断链检测（引用了
[[不存在的页面]]） - 来源可追溯性（insight 是否有对应 source）
输出格式
📊 总评分: XX/100
分项:
- Beat 完整度: XX/30
- 角色弧一致性: XX/30
- 结构健康度: XX/25
- 连接完整性: XX/15
🔴 Error (严重问题，必须修复):
- ...
🟡 Warning (影响质量，建议修复):
- ...
🟢 Good (做得好的地方):
- ...
💡 优先修复建议（按影响排序）:
1. ...
2. ...
3. ...
约束
- 只读操作，不修改任何文件
- 诊断基于客观标准（字段是否存在、是否为空），不做主观内容评判
- 如果 wiki 为空或极度不完整，给出"初始化建议"而非大量错误
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.
- 7d ago First seen · 75 lines · 12 tokens per session scan A 5d3d70f970f3
screenwriting-lint is an agent published in the GitHub repository e06084/claude-screenwriting (6 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 582 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
entity-tracker
Canonical state keeper for the book pipeline. Maintains ENTITYSTATE.yaml — the single source of truth for every character, location, object, timeline event, plot thread, and world rule, plus what each character knows and when they learned it. Builds the state from the outline, then updates it incrementally as chapters…
continuity-guardian
Continuity auditor for the book pipeline. The safety net against plot holes — checks timeline feasibility, character consistency, information flow, plot-thread closure, world-rule integrity, and object continuity against ENTITYSTATE.yaml. Runs once on the outline (pre-writing) and once on the full manuscript. Flags…
dialogue-polish
Surgical dialogue pass for the book pipeline. Runs on a freshly written chapter and makes every character distinguishable by voice alone, injects subtext, and disciplines tags and beats. Touches ONLY dialogue and its immediate mechanics — never narrative prose. Edits the chapter in place and writes a short report.
hook-craft
Chapter opening/ending specialist for the book pipeline. Scores the first lines (hook) and last lines (pull) of a chapter, and if either is below the genre threshold, surgically rewrites only the first/last 3–5 sentences to pull the reader in and refuse to let them stop. Varies hook type across chapters. Edits in…
Slides Wizard
Expert presentation strategist and creative advisor for creating impactful Marp presentations with strategic content and visual design.
canvas-media
Media asset dispatcher for canvas generation. Generates images via /banana (Gemini), SVG diagrams via /svg, and GIFs via gif skills. Returns file paths for placement on canvas. Handles batch generation for multi-image canvases. Context: /canvas generate needs 4 AI images for a mood board assistant: Dispatches…