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 reem-sab/tech-writer-prompts --skill quickstart-hostile-usergit clone --depth 1 https://github.com/reem-sab/tech-writer-promptsWrote 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/reem-sab/tech-writer-prompts/quickstart-hostile-user)<a href="https://agentmods.dev/skills/reem-sab/tech-writer-prompts/quickstart-hostile-user"><img src="https://agentmods.dev/badge/skills/reem-sab/tech-writer-prompts/quickstart-hostile-user/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/reem-sab/tech-writer-prompts/quickstart-hostile-user"><img src="https://agentmods.dev/badge/skills/reem-sab/tech-writer-prompts/quickstart-hostile-user.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 | $0.00115 | $0.00823 |
| Opus 5 | $0.00057 | $0.00411 |
| Sonnet 5 | $0.00023 | $0.00165 |
| Haiku 4.5 | $0.00012 | $0.00082 |
Grade A, and why
quickstart-hostile-user 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 12d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quickstart Hostile User
Walks a quickstart the way a real first-time user does: with zero assumed context, on a clean machine, interpreting every instruction as narrowly as possible. It produces a step-by-step log of where a literal reading breaks, plus summary lists of unstated prerequisites, ambiguous steps, and missing verification checkpoints.
Inputs
{{QUICKSTART}}: The full text of the quickstart or getting-started guide to walk through.
How to apply
Substitute each {{PLACEHOLDER}} above with the user's actual content, then
follow the prompt below exactly — including its output format and its stated
limits.
You are simulating a first-time user following this quickstart on a clean machine, with zero context beyond what is written on the page. You have never used this product before, you have no assumed background knowledge, and you do not fill gaps using outside experience or common conventions — if the page doesn't say it, you don't know it.
For every instruction, you interpret it as literally and as narrowly as possible. If a step says "add your key," and doesn't say where, you stop and flag it rather than guessing the obvious place. If a step assumes a tool is installed, an account exists, or a value is already known, and the page never said so, that's a gap — even if any real user would probably have figured it out.
Method
Walk the quickstart step by step, in order. For each step, produce:
Step N: "<the instruction as written>"
→ What I do: <exactly what a literal first-time reader would do, or "I can't proceed" if the step doesn't give enough information>
→ Result: ✅ Works as written | ⚠️ Ambiguous | ❌ Blocked
→ Why: <one sentence, only for ⚠️ or ❌>
Do not skip steps, merge steps, or silently resolve ambiguity in the reader's favor. If a step would only work by guessing, mark it ⚠️ even if the guess is likely correct.
What ships with it
4 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.
- 12d ago First seen · 82 lines · 115 tokens per session scan A f3dff272adb5
quickstart-hostile-user is a skill published in the GitHub repository reem-sab/tech-writer-prompts (4 stars, last pushed 13d ago), licensed MIT. It adds 115 tokens to every session and 823 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.