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 skills/benchflow-ai/skillsbench/task-creatornpx skills add benchflow-ai/skillsbench --skill task-creatorgit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote 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/benchflow-ai/skillsbench/task-creator)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/task-creator"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/task-creator.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 | $0.00104 | $0.04218 |
| Opus 5 | $0.00052 | $0.02109 |
| Sonnet 5 | $0.00021 | $0.00844 |
| Haiku 4.5 | $0.00010 | $0.00422 |
Grade B, and why
task-creator scanned grade B with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
CODEX_MODEL=gpt-5.5 # adjust per ~/.codex/config.toml Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Bundle frozen inputs (CSVs, xlsx) in `environment/`. For tasks that need internet (research-track), declare the required network and environment policy in `task.md` frontmatter and prefer Playwright over `urllib` for any Copies of this mod
1 near-identical copy found in the catalogue:
- task-creator — 97% identical, 11 lines differ
How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SkillsBench Task Authoring
Build a task that scores well on the task principles. Two artifacts when you're done: a directory under tasks/<task-id>/ that bench tasks check accepts, and a PR description that maps cleanly to the PR template.
Workflow
1. propose → one-paragraph proposal, gut-check against the proposal rubric
2. scaffold → bench tasks init, plus the native task.md layout below
3. task.md → frontmatter + human-written, outcome-focused prompt body
4. environment → Dockerfile + bundled inputs; do NOT bake skills
5. tests → 4–10 test functions, parametrize for bulk; check formulas AND values
6. oracle → human-written reference solution that derives answers
7. skills → 2–3 generalizable skills (or reuse existing ones from /tasks/*/environment/skills/)
8. validate → bench tasks check + oracle eval (must reach 1.0)
9. self-review → invoke task-review skill on the local path
10. agent runs → Opus 4.8 / latest Codex with and without skills
11. submit → PR with the table the template asks for
Each step is described below. Skip a step only if the rubric says it's optional for your track (research / multimodal). Skipping verification will get the PR rejected.
Step 1 — Propose
Before writing files, write a four-bullet proposal answering the proposal-stage rubric:
- What's the task? One paragraph.
- Who does this in real life? Job, domain, why someone pays for it.
- Why do skills help? What domain knowledge is non-obvious without a skill?
- How would you verify it? Specific output files, deterministic tests.
Sanity-check against the seven proposal criteria (motivated · skill-dependent · verifiable · well-specified · solvable · realistic · outcome-verified). If any is shaky, fix the idea before scaffolding. Posting the proposal in #task-ideas is optional but cheap insurance.
What ships with it
14 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.
- assets/Dockerfile.template 1.2 KB
- assets/task.md.template 834 B
- assets/test.sh.template 915 B
- references/instruction-anatomy.md 3.8 KB
- references/oracle-patterns.md 10 KB
- references/tasktype-code.md 5.0 KB
- references/tasktype-excel.md 5.0 KB
- references/tasktype-infrastructure.md 5.3 KB
- references/tasktype-multimodal.md 5.5 KB
- references/tasktype-research.md 5.0 KB
- references/tasktype-scientific.md 6.3 KB
- references/test-design.md 7.9 KB
- references/time-invariance.md 4.9 KB
- scripts/preflight.sh 2.6 KB runs code
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 · 234 lines · 104 tokens per session scan B 2ca85ff63011
task-creator is a skill published in the GitHub repository benchflow-ai/skillsbench (1,745 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 104 tokens to every session and 4,218 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
docx
Word document manipulation with python-docx - handling split placeholders, headers/footers, nested tables.
document-organization-pipeline
End-to-end pipeline for extracting, classifying, and organizing documents by subject.
python-docx
Programmatically read, modify, and create Word documents (.docx) with python-docx library.
pdf-calendar-parsing
Extract calendar events, blocks, and time slots from PDF calendar files using pdfplumber.
csv-data-handling
Loading and parsing CSV files with D3.js, data transformation, and handling missing values.
security-audit-csv-reporting
Generate structured CSV security audit reports from vulnerability data with proper filtering, formatting, and field mapping.