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 infraspecdev/tesseract --skill writing-stylegit clone --depth 1 https://github.com/infraspecdev/tesseractWrote 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/infraspecdev/tesseract/writing-style)<a href="https://agentmods.dev/skills/infraspecdev/tesseract/writing-style"><img src="https://agentmods.dev/badge/skills/infraspecdev/tesseract/writing-style/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/infraspecdev/tesseract/writing-style"><img src="https://agentmods.dev/badge/skills/infraspecdev/tesseract/writing-style.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 | $0.00060 | $0.00915 |
| Opus 5.5 | $0.00024 | $0.00366 |
| Sonnet 5.5 | $0.00012 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
writing-style 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Style
Make Shield doc prose simple, clear, concise, and to the point. This is the single source of truth for "what good Shield prose looks like." Doc-authoring skills apply it to author-written prose before writing the doc out.
Scope — prose only
Apply to author-written prose: problem statements, summaries, narrative sections, outcomes, descriptions, rationale.
Never touch:
- Marker-wrapped or deterministically-rendered regions — e.g. the bytes between
<!-- BEGIN rendered:* -->and<!-- END rendered:* -->(TRD §10 fromrender_trd_section.py). Rewriting these triggersvalidate_trd.pydrift errors (milestone_drift,unbounded_markers). - JSON sidecars, schema-bound field values, stable anchors, code blocks (including inline JSON/YAML/config snippets in the doc itself), and literal command/output samples. "Preserve" means include verbatim in the tightened output — not "don't edit the source file." Dropping a code block as part of cleanup is the same violation as rewriting it.
If unsure whether a region is rendered, leave it untouched.
The four principles
1. Cut filler & redundancy
Delete throat-clearing, hedging, and restated points. Every sentence earns its place.
- ❌ "It is important to note that, at the end of the day, the system is slow."
- ✅ "The system is slow." Cut: "it is important to note", "basically", "in order to", "due to the fact that", "aforementioned", "going forward", "really/genuinely", doubled synonyms.
2. Plain language
Short sentences. Active voice. Common words. Define an unavoidable term once.
- ❌ "Latency reduction will be facilitated by the team."
- ✅ "The team will cut latency."
3. Structure over prose
Prefer tables and bullets to long paragraphs. Lead with the conclusion (BLUF — bottom line up front), then support it.
- ❌ A 6-sentence paragraph listing five requirements.
- ✅ A 5-row bullet list, conclusion sentence first.
4. Concrete & specific
Name real users, numbers, files, outcomes. Replace vague abstractions.
- ❌ "Improve performance."
- ✅ "Cut checkout p95 latency from 800ms to 200ms."
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 · 84 lines · 60 tokens per session scan A 1c058093324e
writing-style is a skill published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 915 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 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
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…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when built-in search is thin. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.