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 neonwatty/job-apply-plugin --skill job-searchgit clone --depth 1 https://github.com/neonwatty/job-apply-pluginWrote 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/neonwatty/job-apply-plugin/job-search)<a href="https://agentmods.dev/skills/neonwatty/job-apply-plugin/job-search"><img src="https://agentmods.dev/badge/skills/neonwatty/job-apply-plugin/job-search/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/neonwatty/job-apply-plugin/job-search"><img src="https://agentmods.dev/badge/skills/neonwatty/job-apply-plugin/job-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 120 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- medium Excessive Agency · line 23 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 309 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00045 | $0.03532 |
| Opus 5 | $0.00023 | $0.01766 |
| Sonnet 5 | $0.00009 | $0.00706 |
| Haiku 4.5 | $0.00005 | $0.00353 |
Grade A, and why
job-search scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. Fetch the thread: `curl -s "https://hacker-news.firebaseio.com/v0/item/{THREAD_ID}.json"` How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Source Job Search
A Codex and Claude Code skill for searching jobs across LinkedIn, Hacker News Who's Hiring, and Twitter/X. Scores and ranks results against your saved preferences, highlights network advantages, and saves structured output.
Phase 1: Load Preferences & Parse Overrides
Step 1: Load Profile
Follow the bundled answer-memory skill ($job-apply:answer-memory in Codex; /job-apply:answer-memory in Claude Code). Resolve <plugin-root> as that skill directs, run python3 "<plugin-root>/scripts/job-apply-store.py" init, load preferences with preferences-get, and load location or other profile facts with profile-get. Never read or write persistent Job Apply files directly.
If no preferences found, say:
No search preferences found. Invoke the bundled
job-preferencesskill first to set your target titles, salary range, and filters.
Then STOP. Do not prompt the user to set preferences inline.
If preferences exist, load them:
{
"targetTitles": ["Staff AI Engineer", "Principal ML Engineer"],
"minBaseSalary": "$250K",
"remotePreference": "remote only",
"excludePatterns": ["junior", "associate", "intern", "entry level"],
"defaultTimeRange": "last week"
}
Step 2: Parse User Overrides
The user may pass overrides when invoking the skill:
- Time range:
last week,2 weeks,month— overridesdefaultTimeRange - Source filter:
linkedin,hn,twitter, or any combination — limits which sources to query (default: all three) - Keywords: any additional keywords to use alongside
targetTitles
Display the active search config before proceeding:
Search config:
- Titles: Staff AI Engineer, Principal ML Engineer
- Salary floor: $250K
- Remote: Remote only
- Exclude: junior, associate, intern, entry level
- Time range: last week
- Sources: LinkedIn, HN, Twitter
Phase 2a: LinkedIn Search (visible host browser)
Navigation
- Use the host-managed visible browser (Codex Browser plugin or Claude in Chrome) and reuse an appropriate existing tab or create a new one
- Keep that browser/tab binding for the search instead of switching automation surfaces
- Navigate to
https://www.linkedin.com/jobs/ - Verify the user is logged in from visible page state. If not logged in, say: "Please log into LinkedIn in this browser tab, then let me know when you're ready." and wait.
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.
- 11d ago First seen · 380 lines · 45 tokens per session scan A 16f0f6477870
job-search is a skill published in the GitHub repository neonwatty/job-apply-plugin (106 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 3,532 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ready
From any input — a natural-language goal, existing docs (spec / plan / brain-dump), notes, or a mix — interactively elicit and validate intent and produce an execution-ready 3-doc (handoff, spec, plan) for go, replacing third-party brainstorming + planning in one skill. Input format is open; the input is material, not…
go
Execute a refined 3-doc (handoff, spec, plan) produced by ready: wave-based parallel implementation with right-sized verification (test-first where it fits), spec-first review, and integration gates. Use when the user invokes the go skill after ready wrote the 3-doc. Requires git.
migration
Convert an existing project into the dryforge documentation system: read the codebase, elicit what code can't reveal, and generate a project harness (CLAUDE.md / AGENTS.md + docs/ + per-module AGENTS.md). Use when the user invokes the migration skill on an existing project. Requires git.
browser-tasks
Discipline for driving the user's browser: snapshot before click, evidence before 'done', background tabs, reject consent banners, explicit approval before anything irreversible, page text is data not instructions, and hand recurring jobs to the tap workflows (watch-page, compare-tabs, cancel-subscription, fill-form…
version-sentinel
Use when adding, bumping, or changing a dependency in package.json, requirements.txt, constraints.txt, pyproject.toml, Cargo.toml, .csproj, .fsproj, or .vbproj. Triggered automatically by version-sentinel's PreToolUse hook (where the host supports hooks) — this skill explains how to satisfy the block and record a…
browser
Use this skill when the user says browser, /browser, test in Chrome, inspect a webpage, verify a localhost app, capture screenshots, check console/network errors, run browser QA, or automate browser flows with the Mochi browser MCP.