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.
git clone --depth 1 https://github.com/niharya/skills-drawerWrote 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/plugins/niharya/skills-drawer/run-candidacy)<a href="https://agentmods.dev/plugins/niharya/skills-drawer/run-candidacy"><img src="https://agentmods.dev/badge/plugins/niharya/skills-drawer/run-candidacy/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/plugins/niharya/skills-drawer/run-candidacy"><img src="https://agentmods.dev/badge/plugins/niharya/skills-drawer/run-candidacy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
run-candidacy 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.
What it actually says
{
"name": "run-candidacy",
"version": "1.0.0",
"description": "One job at a time. Tailored resume, application answers, and outreach contacts — generated from your own facts, written in your own voice. Built for anyone applying to design, product, or frontend roles.",
"author": {
"name": "Nihar Bhagat",
"email": "[email protected]"
},
"license": "MIT",
"repository": "https://github.com/niharya/skills-drawer",
"keywords": [
"resume",
"job-application",
"cover-letter",
"career",
"candidacy",
"tailoring",
"outreach"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 89 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 21 lines scan A 4edba17dc940
run-candidacy is a plugin published in the GitHub repository niharya/skills-drawer (2 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
comfyui
Local-first ComfyUI for Claude Code: drive a local ComfyUI (your GPU, no account) end to end - 75 model prompt recipes, hardware-aware model selection, workflow building, multi-shot video, ControlNet/HDR, the local comfyui-mcp driver. The local-first counterpart to the Comfy Cloud MCP.
anti-slop-design
Eliminates generic AI-generated design from any front-end you build or review, web or mobile. 20 reference modules: the slop taxonomy, personality axes and product registers, mobile and app-screen patterns, trust signals, data visualisation, a craft list, a pre-emit checklist and a worked example.
deglaze
Strip the sycophancy. Makes Claude honestly audit its own claimed-complete work against 17 named under-delivery patterns instead of polishing a summary over half-finished tasks.
pdca
TDD-disciplined AI code generation using Plan-Do-Check-Act methodology. Enforces architecture-first analysis, strict red-green-refactor, Socratic ACT retrospectives, and optional Beads task tracking integration.
promo-video
Turn a website URL into a premium, beat-locked product promo video with Remotion — original design system every time, music-onset-locked scene grid, self-verifying renders, 16:9 + 9:16 + thumbnails.
claude-patterns
Instinct Engine that scans recent sessions, journals, and decisions for recurring patterns and turns them into concrete captures (rules, concept notes, writing seeds, skill improvements). Detects what's hardening into real insight before it evaporates.