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 Neeeophytee/agent-stylebooks --skill nasa-technical-writinggit clone --depth 1 https://github.com/Neeeophytee/agent-stylebooksWrote 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/neeeophytee/agent-stylebooks/nasa-technical-writing)<a href="https://agentmods.dev/skills/neeeophytee/agent-stylebooks/nasa-technical-writing"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/nasa-technical-writing/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/neeeophytee/agent-stylebooks/nasa-technical-writing"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/nasa-technical-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.00801 |
| Opus 5.5 | $0.00028 | $0.00320 |
| Sonnet 5.5 | $0.00014 | $0.00160 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
nasa-technical-writing 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 2mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NASA technical writing
Create a durable technical record from supplied engineering or scientific evidence. Make it possible for a qualified reader to understand what was done, what was observed, and what follows.
Protect the technical record
- Preserve measurements, units, tolerances, significant figures, uncertainty, calibration, configuration identifiers, test conditions, and data exclusions.
- Do not improve, average, convert, or round a value unless the method and authority are supplied.
- Distinguish source data, calculated results, observations, interpretations, requirements, limitations, and recommendations.
- Do not turn correlation into causation or an untested explanation into a finding.
- Mark missing evidence, anomalous data, and unresolved discrepancies for technical review.
Frame the report
- State the purpose: the question, requirement, or decision the work addresses.
- Define scope, system boundary, applicable configuration, and excluded conditions.
- Identify governing requirements, prior work, assumptions, and acceptance criteria.
- Summarize the method and principal result without overstating certainty.
- Choose sections that fit the artifact: background, apparatus, method, results, analysis, limitations, conclusions, and recommendations.
Make methods reproducible
- Describe hardware, software, materials, environment, setup, calibration, sampling, controls, and procedure at the precision needed to repeat or evaluate the work.
- Record departures from the planned method and explain their effect on interpretation.
- Define variables, coordinate systems, reference frames, and conventions before use.
- Keep chronological procedure separate from the rationale for choosing the method.
- Cite the source of externally supplied data and identify any transformation applied to it.
Report evidence before interpretation
- Present observed and calculated results without evaluative language.
- Tie every figure and table to a question in the text. State what the reader should inspect, while keeping interpretation out of captions when that distinction matters.
- Give units in headings or labels and define error bars, limits, and missing values.
- Compare results with requirements or predictions using the stated acceptance method.
- Explain anomalies and competing interpretations; do not discard inconvenient results silently.
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.
- 2mo ago First seen · 79 lines · 70 tokens per session scan A c04e55fcb783
nasa-technical-writing is a skill published in the GitHub repository Neeeophytee/agent-stylebooks (78 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 801 once invoked, about $0.0003 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 2026-08-30.
nasa-technical-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nasa-technical-writingNeeeophytee/agent-stylebooks | Skill | 78 | 2mo ago | MIT | A | 70 | Claude Code, Codex |
| yolo-trainingfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 124 | Claude Code |
| paper-search-usagefcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 57 | Claude Code |
| polish-sci-figureszhoy0409-debug/polish-sci-figures | Skill | 79 | 2d ago | MIT | A | 107 | Codex |
| make-sci-data-figureszhoy0409-debug/polish-sci-figures | Skill | 79 | 2d ago | MIT | A | 96 | Codex |
| standardize-sci-imageszhoy0409-debug/polish-sci-figures | Skill | 79 | 2d ago | MIT | A | 94 | Codex |
| polish-sci-figureszhoy0409-debug/polish-sci-figures | Skill | 79 | 2d ago | MIT | A | 39 | Claude Code, Codex |