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 Boom5426/Nature-Paper-Skills --skill draft-marker-disciplinegit clone --depth 1 https://github.com/Boom5426/Nature-Paper-SkillsWrote 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/boom5426/nature-paper-skills/draft-marker-discipline)<a href="https://agentmods.dev/skills/boom5426/nature-paper-skills/draft-marker-discipline"><img src="https://agentmods.dev/badge/skills/boom5426/nature-paper-skills/draft-marker-discipline/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/boom5426/nature-paper-skills/draft-marker-discipline"><img src="https://agentmods.dev/badge/skills/boom5426/nature-paper-skills/draft-marker-discipline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 139 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00083 | $0.02824 |
| Opus 5 | $0.00042 | $0.01412 |
| Sonnet 5 | $0.00017 | $0.00565 |
| Haiku 4.5 | $0.00008 | $0.00282 |
Grade A, and why
draft-marker-discipline 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Marker Discipline
Overview
A manuscript written across many sessions accumulates open questions. Where those questions live determines whether the draft is auditable or merely long.
Kept in chat, they evaporate at the end of the session. Kept in a separate issue list, they drift out of sync with the sentence they belong to. Kept in the source next to the claim, they survive, they travel with the text, and they can be counted.
This skill covers the marker system, the triage that makes a marker count meaningful, the measurement that makes a length claim honest, and the two mechanical traps that have each cost a real build.
When To Use
Use this skill when:
- a manuscript is drafted across sessions, by several people, or by agents
- you are about to do a batch pass over open markers
- you are about to quote the manuscript's length
- superseded material needs to be removed from the tree
- you are about to make the same edit across many files with a script
Do not use this skill for:
- deciding whether a claim's source supports it. That is
claim-source-verification; this skill is the bookkeeping around it. - restructuring an unstable argument. That is
manuscript-optimizer.
1. Four Markers, Four Jobs
\TODO{...} red an unresolved FACTUAL or SOURCING question
\note{...} blue editorial, addressed to the authors
\directive{...} boxed what must change in this passage, and why
\superseded{...} grey text a freeze decision replaced, kept not deleted
All four vanish under a draft-mode switch, so a clean copy for circulation is one boolean away.
The discipline is the restriction on \TODO. It carries factual and sourcing
questions only, never style notes, never "tighten this", never "consider
rephrasing". Style goes in \note; a required change goes in \directive.
The payoff is that the \TODO count becomes a readiness metric rather than a
mixed bag. "Thirty-seven open TODOs" means thirty-seven unresolved factual
questions, which is a statement about the manuscript's evidentiary state. If
style notes are mixed in, the number means nothing and stops being reported.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 272 lines · 83 tokens per session scan A aa30d3fddeb0
draft-marker-discipline is a skill published in the GitHub repository Boom5426/Nature-Paper-Skills (490 stars, last pushed 7d ago), licensed MIT. It adds 83 tokens to every session and 2,824 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…