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/tasitech/tasi-harness/documentnpx skills add TasiTech/tasi-harness --skill documentgit clone --depth 1 https://github.com/TasiTech/tasi-harnessWrote 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/tasitech/tasi-harness/document)<a href="https://agentmods.dev/skills/tasitech/tasi-harness/document"><img src="https://agentmods.dev/badge/skills/tasitech/tasi-harness/document.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 | $0.00101 | $0.01430 |
| Opus 5 | $0.00051 | $0.00715 |
| Sonnet 5 | $0.00020 | $0.00286 |
| Haiku 4.5 | $0.00010 | $0.00143 |
Grade A, and why
document 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 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.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solution content generation
Scope
This skill controls document content and figure planning: topic understanding, section writing, detail depth, final narrative quality, and where diagrams should appear in the document.
Use this skill when users ask to write, rewrite, expand, or polish document text. When diagrams would improve comprehension, include clear figure placeholders and diagram specifications in the document content. This skill does not directly edit binary Word/PDF/PPT files; use file-format skills for final document packaging.
Workflow
Request → Plan → Draft → Audit → Refine → Deliver
Language-process constraints (no script orchestration required):
- Request: Restate objective, audience, output type, and constraints before drafting.
- Plan: Build a clear section-level outline with intended depth for each section.
- Draft: Produce a complete first draft (not skeleton bullets) following the plan.
- Audit: Check structure, factual consistency, clarity, actionability, and audience fit.
- Refine: Revise weak sections with concrete detail; remove repetition and vague claims.
- Deliver: Return a polished final version with clear conclusions and next actions when applicable.
Complexity gate (must decide before writing):
- Treat as complex when any of the following is true: multi-section deliverable, high-stakes audience, requested depth is standard/thorough, non-trivial constraints (policy/compliance/format/terminology), or requested length exceeds short memo scope.
- Treat as simple when the request is short, low-risk, single-purpose, and can be completed with one concise pass.
Execution rules:
- For complex tasks, follow all six stages in order and do not skip stages.
- For simple tasks, stage merging is allowed (for example, Request+Plan or Audit+Refine), but the output must still meet quality requirements.
- If information is missing, state assumptions explicitly and continue.
- Keep outputs substantive by default unless the user explicitly requests brevity.
- If the user asks for only one stage (for example, outline only), comply while preserving quality standards for that stage.
- Match the user's language by default unless they request another language.
- Do not fabricate specific facts, metrics, citations, or policy details; mark uncertain items clearly.
- When the document would benefit from a visual, plan the figure location during Plan, draft the surrounding explanation during Draft, and verify every figure has a purpose, title, and source/specification during Audit. See diagram-inserts.md for diagram placement rules and data-chart-inserts.md for data chart planning rules.
- For formal方案/设计文档, require Draw.io diagram sources and exported PNG/SVG assets for all required design figures. Do not use Mermaid. The final document package is incomplete until exported images are embedded in the Word/PDF/PPTX body near their relevant sections.
What ships with it
3 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.
- 4d ago First seen · 91 lines · 101 tokens per session scan A 452906af2bbe
document is a skill published in the GitHub repository TasiTech/tasi-harness (11 stars, last pushed 5d ago), licensed MIT. It adds 101 tokens to every session and 1,430 once invoked, about $0.0005 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
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…