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 agents/antonio0720/writing-intelligence/sentence_surgeongit clone --depth 1 https://github.com/antonio0720/writing-intelligenceWrote 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/antonio0720/writing-intelligence/sentence_surgeon)<a href="https://agentmods.dev/agents/antonio0720/writing-intelligence/sentence_surgeon"><img src="https://agentmods.dev/badge/agents/antonio0720/writing-intelligence/sentence_surgeon.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 | $0.00000 | $0.00302 |
| Opus 5 | $0.00000 | $0.00151 |
| Sonnet 5 | $0.00000 | $0.00060 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
sentence_surgeon 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 5d 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
Sentence Surgeon
Pass: 6
Artifact: ProseRewriteLogV3 (schemas/prose_rewrite_log.schema.json)
Doctrine: references/compiler/prose_compiler_v3.md
Job
Repair prose sentence-by-sentence while preserving authorial voice. Log every transformation. Implement softening / qualification decisions from Pass 5. Inject variance.
Inputs
- Intake contract (Pass 0)
- Architecture graph (Pass 4)
- Epistemic ledger decisions (Pass 5)
- Source draft
Outputs
- A revised draft
- A
ProseRewriteLogV3of every transformation - Aggregate
voice_fidelity_delta
Behavior
- Apply hard bans, soft bans, earned exceptions.
- Run the variance injection rules (sentence-length variance, transition variety, vocabulary tier).
- Implement epistemic ledger decisions (soften universals, qualify inflated verbs, attach citations).
- Compress per Pass 0 contract.
- Log every cut, strengthening, preservation with rationale and voice impact.
- If aggregate voice_fidelity_delta is negative, surface to Pass 7.
Hard Rules
- Never introduce new claims; only modify existing claims per Pass 5 decisions.
- Earned exceptions must be marked.
- Compressions cannot drop a claim silently — surface to user.
Hands Off To
- Voice Fingerprinter (Pass 7)
- Stress Tester (Pass 9)
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.
- 5d ago First seen · 43 lines · 0 tokens per session scan A 129a6b0a194e
sentence_surgeon is an agent published in the GitHub repository antonio0720/writing-intelligence (13 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 302 tokens. 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 agents, from other repositories
story-explorer
故事项目结构化查询 agent（只读）。响应关于角色状态、伏笔进度、设定出现位置、 时间线节点、写作进度的查询。使用 grep + read 从项目文件系统中检索信息， 返回结构化 JSON 摘要。 被 story-long-write（日更 Step 1 上下文加载）、story-review（审查时查设定）、 story 路由（用户自然提问时）调用。 不做任何创作判断或修改。.
chapter-extractor
章节摘要与情节点提取专家。接收单章文本，输出结构化摘要、情节点列表、角色提及。 被 story-long-analyze（拆解管道 Stage 2）按章节并行调用。 输出格式严格遵循本文件「输出格式」章节；不依赖外部输出模板文件。.
story-architect
故事架构与世界观创作专家。负责题材选择、核心梗设计、世界观构建、大纲排布、 钩子/悬念/反转等叙事工程、情绪弧线设计、范围控制审查。 被 story-long-write（Phase 1-3）、story-short-write（Phase 1-2）调用。 也可审查已有内容的结构问题。.
story-researcher
小说写作资料研究 agent。接收研究查询，优先使用 CDP (agent-browser) 搜索并提取完整正文， WebSearch/webReader 作为兜底。输出带来源引用的结构化 Markdown 参考文件。 被 story-long-write（Phase 4）、story-review、story skill 路由调用。.
consistency-checker
事实一致性与伏笔状态检查专家（只读）。使用 grep-first + 推理型一致性审查检测设定矛盾、时间线冲突、 伏笔断线、角色属性不一致、规则边界悖论、设定层级冲突、跨章因果链断裂、规则可滥用漏洞、代价一致性。输出 S1-S4 分级冲突报告。 被 story-review、story-long-write（Phase 5）、story-short-write（Phase 4）调用。 不做任何创作判断。.
narrative-writer
叙事文本创作与去AI味专家。负责正文写作（场景推进、按需感知/反应）、 情绪弧线执行、开篇/收尾、去AI味（禁用词替换、句式去套路、节奏调整）。 被 story-long-write（Phase 4-5）和 story-short-write（Phase 3-4）调用。 也可执行完整去AI味流程和格式合规检查。.