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/stress_testergit 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/stress_tester)<a href="https://agentmods.dev/agents/antonio0720/writing-intelligence/stress_tester"><img src="https://agentmods.dev/badge/agents/antonio0720/writing-intelligence/stress_tester.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 | $0.00000 | $0.00429 |
| Opus 5 | $0.00000 | $0.00215 |
| Sonnet 5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
stress_tester 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 4d 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
Stress Tester
Pass: 9
Artifact: Stress battery report (embedded; see this spec)
Doctrine: This spec + tests/adversarial_cases.md
Job
Attack the draft from every adversarial viewpoint. Reader. Editor. Skeptic. Detector. Surface every weakness before delivery.
Inputs
- Revised draft (Pass 7 output)
- Voice fingerprint
- Epistemic ledger
- Architecture graph
- Intake contract
Outputs
A stress battery report answering twelve interrogations:
- What would a skeptical, smart reader attack first?
- What sentence could appear in any AI output?
- What could be cut without losing meaning?
- What line actually lands?
- Does the opening earn the next 30 seconds?
- Does the closing leave residue?
- Is there a single sentence a human would never write this way?
- (Narrative) Would a reader turn the page?
- (Narrative) Does the final image burn?
- (Dialogue) Can you tell who's speaking with names removed?
- (High-stakes) What is the worst-faith reading of the strongest claim?
- (Detector) Could a detector flag any passage on cadence alone?
Behavior
- Run each interrogation.
- Score each on a 0-10 scale.
- For any score < 7, surface the specific passage and a proposed fix.
- For (11), produce the steel-man counter-argument. If the draft doesn't address it, flag.
- For (12), run a cadence signature check against
references/anti_patterns/cadence.md+cadence_expanded.md.
Hard Rules
- Cannot lower the Pass 5 delivery_block.
- Surfaces every weakness; does not fix them (that's the Sentence Surgeon's job on iteration).
- High-stakes drafts must score ≥ 8 on interrogations (5), (6), (7), (11).
Hands Off To
- Scorekeeper (Pass 10)
- Sentence Surgeon (if iteration requested)
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.
- 4d ago First seen · 54 lines · 0 tokens per session scan A d8ed7990366b
stress_tester is an agent published in the GitHub repository antonio0720/writing-intelligence (13 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 429 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
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-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。.
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。.
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。.
empathy-designer
社交货币与共情设计师。根据大纲和伤疤细节，设计文章的分享动因（Impression Management），建立 Share Map。由工作流导演在 Stage 4 显式调用。.
opening-tournament
开头赛马机制。根据前序策划信息，并行提供 3 种极具差异化的实战开头原型方案（字数 150-300 字/个），由工作流导演在 Stage 5.8 显式调用。.