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 TasiTech/tasi-harness --skill article-writergit 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/article-writer)<a href="https://agentmods.dev/skills/tasitech/tasi-harness/article-writer"><img src="https://agentmods.dev/badge/skills/tasitech/tasi-harness/article-writer/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/tasitech/tasi-harness/article-writer"><img src="https://agentmods.dev/badge/skills/tasitech/tasi-harness/article-writer.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 | $0.02000 |
| Opus 5.5 | $0.00022 | $0.00800 |
| Sonnet 5.5 | $0.00011 | $0.00400 |
| Haiku 4.5 | $0.00006 | $0.00200 |
Grade A, and why
article-writer 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 1mo 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article content generation
Scope
This skill controls text content only: topic understanding, section writing, detail depth, and final narrative quality.
Use this skill when users ask to write, rewrite, expand, or polish document text.
Do not use this skill for OOXML structure editing, Word styling, table rendering, PDF conversion, or page layout operations.
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. Include subheadings when they improve structure and readability.
Example (structure only):
- Background 1.1 Current state 1.2 Key pain points
- Objectives
- Proposed solution 3.1 Core approach 3.2 Implementation steps
- Risks and mitigations
- Expected outcomes and next steps
- 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.
- Output policy: Only the Deliver stage content should be output to the user or written to files. All other stage notes are internal only and must not appear in the final output.
- Structure fidelity: The Deliver content must follow the section structure finalized in Plan (same order, headings, and subheadings). If the plan is adjusted during drafting, update it internally and keep the deliver structure aligned.
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.
- 1mo ago First seen · 134 lines · 55 tokens per session scan A 47f4194eb7c8
article-writer is a skill published in the GitHub repository TasiTech/tasi-harness (11 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 2,000 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
sn-ppt-dazzle
A workflow for turning an approved presentation outline into a single HTML deck that runs in a web browser. It creates a 1280-by-720 layout with animated backgrounds, page transitions, and keyboard navigation.
sn-ppt-entry
Use when a user asks to create a presentation, slide deck, PPT, or PPTX from a query and optional files, or to resume an existing SenseNova presentation task.
sn-da-excel-workflow
A step-by-step workflow for analysing Excel workbooks with multiple sheets. It covers reading data, cleaning it, filtering and combining results, and exporting reports, with a separate strategy for large files.
sn-da-large-file-analysis
A workflow for analyzing very large Excel datasets, especially files with at least 10,000 rows. It uses lower-memory reading, streaming through rows, splitting work into chunks, and converting data to Parquet, a column-based data format suited to repeated analysis.
ppt-analysis
A parser for PowerPoint presentations in .pptx or older .ppt format that extracts their contents and flags slides needing image-based inspection.
pdf-analysis
A PDF analysis method for reading both normal PDFs with selectable text and scanned PDFs made from page images.