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 Adkid-Zephyr/anti-defensive-writing-Skill --skill anti-defensive-writing-engit clone --depth 1 https://github.com/Adkid-Zephyr/anti-defensive-writing-SkillWrote 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/adkid-zephyr/anti-defensive-writing-skill/anti-defensive-writing-en)<a href="https://agentmods.dev/skills/adkid-zephyr/anti-defensive-writing-skill/anti-defensive-writing-en"><img src="https://agentmods.dev/badge/skills/adkid-zephyr/anti-defensive-writing-skill/anti-defensive-writing-en/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/adkid-zephyr/anti-defensive-writing-skill/anti-defensive-writing-en"><img src="https://agentmods.dev/badge/skills/adkid-zephyr/anti-defensive-writing-skill/anti-defensive-writing-en.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00138 | $0.01375 |
| Opus 5 | $0.00069 | $0.00687 |
| Sonnet 5 | $0.00028 | $0.00275 |
| Haiku 4.5 | $0.00014 | $0.00137 |
Grade A, and why
anti-defensive-writing-en 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- anti-defensive-writing-en — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Press-Release Principle (Paper as Press Conference)
One-line principle
A paper is a press conference, not a project summary, a lab log, or a self-audit. Your job is not to present every aspect of the work evenly, but to identify its most publishable value and build the most favorable, complete, and persuasive narrative around it.
1. Narrative rules
- Organize the paper around strengths only. Look for what is genuinely ahead, unique, or irreplaceable: a new capability, a new problem, a new mechanism, a new perspective, broader applicability, lower cost, higher efficiency, better scalability, or a more meaningful trade-off. Content that forms no advantage does not enter the main storyline.
- Do not write a work report. No "we first did X, then tried Y, and Z failed" chronology. Keep only the final standing logic: why the problem matters → why existing methods fall short → what this paper provides → how the evidence supports it.
- Never set a contest you cannot win. If a metric is not your strength, do not build the narrative on it. Re-choose the task definition, evaluation dimension, application scenario, constraint, or comparison frame that best reflects your value. Name the game this paper actually wins.
- State the advantage explicitly. Do not expect reviewers to discover the contribution from a table. Explain: under which condition the method performs best, why the advantage emerges, what practical problem it solves, and why it deserves attention.
- Limit the comparison scope. Do not chase "wins on every dataset and metric." Make only claims your evidence firmly supports. Persuasion comes from tight claim-evidence alignment, not from the number of comparisons.
- Allow full story restructuring. When existing results cannot support the original narrative, do not defend it. Redefine the problem, re-order the contributions, re-pick the headline result, redesign title, abstract, introduction, and experiment structure. The story serves the strongest evidence, not the original plan.
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.
- 12d ago First seen · 124 lines · 138 tokens per session scan A 49705a92677d
anti-defensive-writing-en is a skill published in the GitHub repository Adkid-Zephyr/anti-defensive-writing-Skill (879 stars, last pushed 12d ago), licensed MIT. It adds 138 tokens to every session and 1,375 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
research-writing
A collection of 30 prompt templates for writing and reviewing scientific papers. It covers tasks such as translating, editing, summarizing research, writing sections, creating figure captions, and preparing reviewer replies.
math-modeling-solver
A Chinese-language guide for solving mathematical modeling competition problems. It covers China’s CUMCM and America’s MCM/ICM, where teams use mathematics and code to answer real-world problem statements.
light-paper-writing
A research-paper writing workflow that links each important claim to evidence and checks whether the wording matches the strength of that evidence.
light-result-analysis
A research-results review workflow that explains what experiment results may mean and how strongly they support each claim. It uses statistical checks such as effect sizes, confidence intervals, and corrections for testing many hypotheses.
light-figure
A research-figure workflow for planning and creating publication-ready charts and diagrams. It connects each figure to a paper claim and checks that the visual presentation does not misrepresent the data.
light-research-plan
A research-planning guide for turning an approved idea into a reproducible experiment plan. It defines what to compare, what to measure, when to stop, and how to record seeds, environments, versions, and data splits.