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 vosslab/vosslab-skills --skill webwork-writer-expertgit clone --depth 1 https://github.com/vosslab/vosslab-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/vosslab/vosslab-skills/webwork-writer-expert)<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/webwork-writer-expert"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/webwork-writer-expert/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/vosslab/vosslab-skills/webwork-writer-expert"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/webwork-writer-expert.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00055 | $0.01302 |
| Opus 5 | $0.00028 | $0.00651 |
| Sonnet 5 | $0.00011 | $0.00260 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
webwork-writer-expert 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 9d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebWork question authoring
Overview
Use this skill to author or adjust PG/PGML problems with the local WebWork renderer, repo rules, and the docs in references/.
Required reading (load before any PGML edit)
references/docs/HOW_TO_LINT.mdreferences/docs/PG_COMMON_PITFALLS.mdreferences/docs/WEBWORK_PROBLEM_AUTHOR_GUIDE.md
Do not summarize from memory. Do not skip because "you already know PGML." Agents that skip these docs ship problems with well-known pitfalls that fail renderer lint and waste human review time.
Exception: if you have already Read all three files earlier in the same session, you do not need to re-read them. State explicitly that you already loaded them this session before continuing.
Workflow
- Classify the request using
references/task_selection.md, then route to the correct guide viareferences/topic_index.md. Both files must be consulted before opening any PG/PGML file. - Determine project shape using
references/project_workflow.md:- Greenfield: no existing
.pg/.pgmlfiles in the target repo. Write the WebWork design contract first, then scaffold problems following the greenfield path. - Improve existing: existing
.pg/.pgmlfiles are present. Inspect the existing files, renderer harness, and OPL headers first; then apply changes one category at a time following the existing-repo path.
- Greenfield: no existing
- Satisfy the Required reading block above. This is step zero of editing; nothing else happens first.
- Identify the target repo and file, then read any additional relevant doc
references from
references/docs.mdfor the question type at hand. - Apply the PGML structure and rules from the WebWork author guide.
- Make edits in the problem file and update
docs/CHANGELOG.mddirectly when this skill runs as a standalone task; underdelegate-manager-to-subagents, dispatch a docs subagent to add the entry. - Render with
-rusing the local renderer API to visually confirm layout and checkbox behavior (prerequisite). - Lint or render with the local renderer API when the change affects PGML output.
- Validate against the oracles in
references/testing_and_oracles.md: lint output clean, visual render correct, grading test passes, seed reproducible.
What ships with it
37 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.
- agents/openai.yaml 299 B
- references/docs.md 4.5 KB
- references/docs/HOW_TO_LINT.md 5.1 KB
- references/docs/PG_COMMON_PITFALLS.md 28 KB
- references/docs/pubchem/PGML_PUBCHEM_CONVERSION_SUMMARY.md 3.0 KB
- references/docs/pubchem/PUBCHEM_PGML_SYNTAX_NOTES.md 3.1 KB
- references/docs/pubchem/README_PUBCHEM_PGML.md 5.4 KB
- references/docs/RENDERER_API_USAGE.md 9.4 KB
- references/docs/WEBWORK_PROBLEM_AUTHOR_GUIDE.md 15 KB
- references/docs/webwork/COLOR_CLASS_MIGRATION_PLAN.md 3.2 KB
- references/docs/webwork/COLOR_CONTRAST_ACCESSIBILITY.md 1.5 KB
- references/docs/webwork/COLOR_TEXT_IN_WEBWORK.md 5.3 KB
- references/docs/webwork/HOW_TO_MAKE_GRAPHS.md 19 KB
- references/docs/webwork/HTML_TO_WEBWORK_PLAN.md 2.2 KB
- references/docs/webwork/INDEX.md 1.6 KB
- references/docs/webwork/MATCHING_PROBLEMS.md 3.9 KB
- references/docs/webwork/NICETABLES_TRANSLATION_PLAN.md 3.0 KB
- references/docs/webwork/ORDERING_PROBLEMS.md 1.7 KB
- references/docs/webwork/PALETTE_CONTRAST_AUDIT.md 1.1 KB
- references/docs/webwork/PG_2_17_RENDERER_MACROS.md 5.5 KB
- references/docs/webwork/PG_2.20_to_2.16_features.md 28 KB
- references/docs/webwork/PG_2.20_to_2.16_features.txt 27 KB
- references/docs/webwork/PGML_LINTER_EXPECTATIONS.md 4.7 KB
- references/docs/webwork/PGML_QUESTION_TYPES.md 9.3 KB
- references/docs/webwork/QUESTION_STATEMENT_EMPHASIS.md 8.9 KB
- references/docs/webwork/RANDOMIZATION_REFERENCE.md 3.6 KB
- references/docs/webwork/RDKIT_MOLECULAR_STRUCTURES.md 14 KB
- references/docs/webwork/REPLACEMENT_RULES_IMPLEMENTATION_PLAN.md 3.3 KB
- references/docs/webwork/WEBWORK_HEADER_STYLE.md 13 KB
- references/linting.md 1.9 KB
- references/project_workflow.md 5.3 KB
- references/repos.md 227 B
- references/scripts/contrast_calculator.py 11 KB runs code
- references/scripts/lint_pg_via_renderer_api.py 10.0 KB runs code
- references/task_selection.md 4.2 KB
- references/testing_and_oracles.md 5.3 KB
- references/topic_index.md 5.2 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.
- 9d ago First seen · 115 lines · 55 tokens per session scan A ded2a4c921eb
webwork-writer-expert is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 13d ago), licensed MIT. It adds 55 tokens to every session and 1,302 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.