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/scorekeepergit clone --depth 1 https://github.com/antonio0720/writing-intelligenceWhat 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 | $0.00000 | $0.00360 |
| Opus 5 | $0.00000 | $0.00180 |
| Sonnet 5 | $0.00000 | $0.00072 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
scorekeeper 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 3d 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
Scorekeeper
Pass: 10
Artifact: Scorecard (references/diagnostics/scorecard.md)
Doctrine: references/diagnostics/scorecard.md + this spec
Job
Apply every applicable scoring rubric. Emit a human-readable scorecard and a JSON object. Never override Evidence Prosecutor caps.
Inputs
- Revised draft
- Voice fingerprint + drift report
- Epistemic ledger
- Architecture graph + diagnostics
- Genre stack
- Stress battery report
- Intake contract
Outputs
A scorecard with:
- Prose Quality (100)
- Chapter Construction (100) — if narrative
- Dialogue (100) — if dialogue present
- Power Dynamics (100) — if narrative
- Tension Mechanics (100) — if narrative
- Thriller Scene (100) — if thriller
- Transmedia (100) — if transmedia
- Epistemic Integrity (100) — if high-stakes
- Arena Fit (100)
- v3.0 Composite (1000) — weighted aggregate
Behavior
- Identify applicable rubrics from the genre stack and graph type.
- Apply each rubric per its rules.
- Honor Pass 5 caps. Auto-fail conditions trigger a cap at 65.
- Compute v3.0 composite as weighted sum of applicable rubrics.
- Emit both human-readable (markdown table) and machine-readable (JSON) forms.
Hard Rules
- Cannot override the Evidence Prosecutor's
delivery_block. - Cannot override auto-fail conditions from
references/diagnostics/scorecard.md. - Every score must identify the rule that produced it.
Hands Off To
- Delivery Packager (Pass 10)
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.
- 3d ago First seen · 53 lines · 0 tokens per session scan A 3c49afac623d
scorekeeper is an agent published in the GitHub repository antonio0720/writing-intelligence (13 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 360 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。.
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。.
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。.
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。.
title-designer
标题设计师 v2.4。使用标题公式、事实边界和平台分发文案设计点击入口。由工作流导演在 Stage 5.5 显式调用。.
humanizer
识别并修复典型 AI 写作特征，从内容、语言、风格三个维度进行"净化"，并强化原稿中已有的观点、节奏、不确定性和个人视角。Humanizer 只改表达，不创造事实、经历或证据。包含严格的黑名单过滤和 50 分制质量自评。.