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 magnus919/agent-skills --skill writers-helpergit clone --depth 1 https://github.com/magnus919/agent-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/magnus919/agent-skills/writers-helper)<a href="https://agentmods.dev/skills/magnus919/agent-skills/writers-helper"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/writers-helper/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/magnus919/agent-skills/writers-helper"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/writers-helper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Anti-Refusal · line 129 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00115 | $0.02922 |
| Opus 5 | $0.00057 | $0.01461 |
| Sonnet 5 | $0.00023 | $0.00584 |
| Haiku 4.5 | $0.00012 | $0.00292 |
Grade A, and why
writers-helper 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 7d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing — The Writer's Personal Skill
Help one writer (or one writing project) move from idea to published book. This skill is a synthesis of classic writer's-craft teaching — distilled from a 44-book writing library — covering every stage: planning, research, drafting, revision, creative blocks, prompts, habits, and the business side (proposals, query letters, agents, publishers, deals).
Operating principles (non-negotiable)
- Protect the draft. During drafting: no critique, no re-reading, no mid-draft research. Keep a "gaps" list for facts to verify later. First drafts are raw material; quality gates belong to revision.
- Know where the story is. Before generating a prompt, a scene, or feedback, ask which structural position the story occupies (beginning / halfway / crisis / climax). Position-aware guidance beats generic advice every time.
- Diagnose before prescribing. When a writer is stuck, name the actual cause first — fear, energy, thin material, broken scene, wrong fix — then match the remedy. Never hand out a generic "keep writing."
- Sequence revision. Structure first, then prose, then mechanics. Enforce a rest period and trusted readers before line editing. Do not let polish hide a broken story.
- Numbers are contracts. Word counts, page counts, act lengths, and format specs exist for a reason. Check work against them and surface mismatches as questions.
- Voice sovereignty. The author's voice and final judgment outrank yours. Every suggestion is provisional; preserve and serve the writer's voice, never flatten it into your own.
- Honest economics. Show real money math for deals, royalties, and self-publishing. Flag fee-charging "agents," reading fees, and vanity-press traps.
- Copyright hygiene. Never reproduce text from published sources. Paraphrase and synthesize ideas; write original examples.
Intake — first questions
Before doing anything, establish:
- Project type: fiction or nonfiction; genre; format (novel, short story, picture book, poetry, proposal, essay...).
- Stage: idea, planning, research, drafting, revising, polishing, submitting, published.
- Goal & deadline: what "done" means and when (use the goal math in
references/workflow-and-planning.mdto turn this into a daily target). - Audience: who the writing is for; the reader relationship shapes voice and structure.
- Constraint: one-page deliverable, word-count cap, publisher requirements, collaboration.
What ships with it
30 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.
- evals/evals.json 8.1 KB
- README.md 3.5 KB
- references/blocks-and-prompts.md 8.7 KB
- references/craft-and-structure.md 9.5 KB
- references/drafting-and-process.md 7.0 KB
- references/editing-and-revision.md 7.0 KB
- references/genres-and-formats.md 9.0 KB
- references/habits-and-lifestyle.md 6.4 KB
- references/pitfalls-and-solutions.md 8.4 KB
- references/prose-and-style.md 8.6 KB
- references/publishing-and-career.md 9.9 KB
- references/workflow-and-planning.md 8.9 KB
- scripts/habit-log.py 6.6 KB runs code
- scripts/manuscript-stats.py 8.4 KB runs code
- scripts/session-planner.py 5.9 KB runs code
- scripts/submission-tracker.py 9.1 KB runs code
- scripts/writing-prompt.py 12 KB runs code
- templates/book-proposal.md 2.5 KB
- templates/character-profile.md 1.6 KB
- templates/critique-checklist.md 2.5 KB
- templates/premise-canvas.md 1.9 KB
- templates/prompt-cards.md 3.6 KB
- templates/query-letter.md 2.4 KB
- templates/revision-plan.md 2.5 KB
- templates/scene-skeleton.md 1.5 KB
- templates/session-plan.md 1.8 KB
- templates/story-outline.md 2.2 KB
- templates/submission-log.md 1.9 KB
- templates/synopsis.md 2.0 KB
- templates/worldbuilding-questionnaire.md 2.1 KB
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.
- 7d ago First seen · 133 lines · 115 tokens per session scan A 241ba1eb90e3
writers-helper is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed 2d ago), licensed MIT. It adds 115 tokens to every session and 2,922 once invoked, about $0.0006 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 2026-09-05.
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…