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 sayantan94/AppliedIn --skill site-quirksgit clone --depth 1 https://github.com/sayantan94/AppliedInWrote 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/sayantan94/appliedin/site-quirks)<a href="https://agentmods.dev/skills/sayantan94/appliedin/site-quirks"><img src="https://agentmods.dev/badge/skills/sayantan94/appliedin/site-quirks/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/sayantan94/appliedin/site-quirks"><img src="https://agentmods.dev/badge/skills/sayantan94/appliedin/site-quirks.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 | $0.00082 | $0.01172 |
| Opus 5.5 | $0.00033 | $0.00469 |
| Sonnet 5.5 | $0.00016 | $0.00234 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
site-quirks 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site quirks
Rules for sites where the generic apply logic is not enough. Each file holds one site's quirks and is injected into the apply task for that site only.
Available sites
By ATS — applies to every posting on that system
| ATS | File | Matches |
|---|---|---|
| Ashby | ashby.md | ashbyhq.com |
| Greenhouse | greenhouse.md | greenhouse.io, boards.greenhouse.io, job-boards.greenhouse.io |
| Workday | workday.md | myworkdayjobs.com, myworkdaysite.com |
By company — applies to that employer only
| Company | File | Why it needs one |
|---|---|---|
| Airbnb | companies/airbnb.md | embedded form, combobox-heavy |
| Anthropic | companies/anthropic.md | combobox-heavy |
| Cerebras | companies/cerebras.md | sanctions question |
| Databricks | companies/databricks.md | embedded form, off-site redirect |
| Datadog | companies/datadog.md | embedded form, combobox-heavy |
| Figma | companies/figma.md | combobox-heavy |
| Google DeepMind | companies/google-deepmind.md | combobox-heavy |
| Nebius | companies/nebius.md | embedded form, combobox-heavy |
| Notion | companies/notion.md | sanctions question |
| OpenAI | companies/openai.md | sanctions question |
| Replit | companies/replit.md | sanctions question |
| Rivian | companies/rivian.md | sanctions question |
| Scale AI | companies/scale-ai.md | combobox-heavy |
| Snowflake | companies/snowflake.md | sanctions question |
| Stripe | companies/stripe.md | embedded form, combobox-heavy |
| Uber | companies/uber.md | off-site redirect |
| Vercel | companies/vercel.md | combobox-heavy |
What ships with it
24 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.
- apple.md 5.1 KB
- ashby.md 4.9 KB
- companies/airbnb.md 515 B
- companies/anthropic.md 262 B
- companies/cerebras.md 192 B
- companies/databricks.md 1.5 KB
- companies/datadog.md 516 B
- companies/figma.md 254 B
- companies/google-deepmind.md 274 B
- companies/nebius.md 514 B
- companies/notion.md 188 B
- companies/openai.md 188 B
- companies/replit.md 188 B
- companies/rivian.md 188 B
- companies/scale-ai.md 261 B
- companies/snowflake.md 194 B
- companies/stripe.md 515 B
- companies/uber.md 460 B
- companies/vercel.md 257 B
- google.md 2.3 KB
- greenhouse.md 2.2 KB
- microsoft.md 3.6 KB
- oracle.md 5.1 KB
- workday.md 4.1 KB
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 · 99 lines · 82 tokens per session scan A f7de22b97ed9
site-quirks is a skill published in the GitHub repository sayantan94/AppliedIn (8 stars, last pushed 13d ago), licensed MIT. It adds 82 tokens to every session and 1,172 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 2026-08-31.
site-quirks compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| site-quirkssayantan94/AppliedIn | Skill | 8 | 13d ago | MIT | A | 82 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | yesterday | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 895 | yesterday | MIT | A | 40 | Claude Code |