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/Rahulchaube1/-Skills-for-AgentsWrote 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/rahulchaube1/-skills-for-agents/skills-for-agents)<a href="https://agentmods.dev/plugins/rahulchaube1/-skills-for-agents/skills-for-agents"><img src="https://agentmods.dev/badge/plugins/rahulchaube1/-skills-for-agents/skills-for-agents/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/rahulchaube1/-skills-for-agents/skills-for-agents"><img src="https://agentmods.dev/badge/plugins/rahulchaube1/-skills-for-agents/skills-for-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-skills 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What it installs
The manifest is a name and a version. 64 skills, 7 commands travel with it, and installing the plugin installs all of them — 2,493 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill code-review-and-quality A 51 tokens
- Skill code-simplification A 51 tokens
- Skill doubt-driven-development A 67 tokens
- Skill interview-me A 108 tokens
- Skill test-driven-development A 50 tokens
- Skill api-and-interface-design A 49 tokens
- Skill ci-cd-and-automation A 45 tokens
- Skill context-engineering A 43 tokens
- Skill debugging-and-error-recovery A 53 tokens
- Skill frontend-ui-engineering A 48 tokens
- Skill git-workflow-and-versioning A 40 tokens
- Skill incremental-implementation A 52 tokens
- Skill performance-optimization A 45 tokens
- Skill security-and-hardening A 48 tokens
- Skill shipping-and-launch A 45 tokens
- Skill using-skills-for-agents A 51 tokens
- Skill deprecation-and-migration A 45 tokens
- Skill documentation-and-adrs A 43 tokens
- Skill idea-refine A 75 tokens
- Skill source-driven-development A 40 tokens
- Skill spec-driven-development A 43 tokens
- Skill planning-and-task-breakdown A 56 tokens
- Skill a11y-automation A 32 tokens
- Skill agent-tooling-design A 38 tokens
- Skill animation-implementation A 30 tokens
- Skill api-versioning A 23 tokens
- Skill browser-automation A 26 tokens
- Skill caching-strategy A 29 tokens
- Skill content-modeling A 26 tokens
- Skill content-strategy A 29 tokens
- Skill contract-testing A 21 tokens
- Skill dashboard-design A 29 tokens
- Skill data-visualization A 30 tokens
- Skill dependency-hygiene A 30 tokens
- Skill design-system-implementation A 25 tokens
- Skill documentation-architecture A 30 tokens
- Skill edge-rendering A 26 tokens
- Skill error-message-design A 25 tokens
- Skill evaluation-harness-design A 36 tokens
- Skill form-ux-patterns A 30 tokens
- Skill incident-response A 27 tokens
- Skill knowledge-base-design A 29 tokens
- Skill localization-internationalization A 33 tokens
- Skill localization-review A 24 tokens
- Skill modularization A 27 tokens
- Skill monorepo-management A 30 tokens
- Skill offline-first A 25 tokens
- Skill onboarding-flows A 27 tokens
- Skill performance-budgeting A 25 tokens
- Skill product-copywriting A 25 tokens
- Skill prompt-architecture A 30 tokens
- Skill prompt-ops A 26 tokens
- Skill refactor-planning A 26 tokens
- Skill release-notes-writing A 30 tokens
- Skill search-and-discovery A 31 tokens
- Skill security-checkpointing A 23 tokens
- Skill state-machine-design A 28 tokens
- Skill technical-writing A 29 tokens
- Skill telemetry-and-observability A 31 tokens
- Skill test-fixture-design A 35 tokens
- Skill user-research-synthesis A 27 tokens
- Skill visual-regression A 26 tokens
- Skill workflow-orchestration A 27 tokens
- Skill browser-testing-with-devtools B 68 tokens
- Command ship A 21 tokens
- Command code-simplify A 16 tokens
- Command review A 18 tokens
- Command build A 16 tokens
- Command plan A 13 tokens
- Command spec A 13 tokens
- Command test A 24 tokens
What ships with it
1 file beside plugin.json 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.
- 1mo ago First seen · 19 lines scan A 32623b548844
agent-skills is a plugin published in the GitHub repository Rahulchaube1/-Skills-for-Agents (2 stars, last pushed 4mo ago), with no licence file. 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
datoon
Smart JSON-to-TOON conversion with pragmatic auto-gating for LLM prompts.
prompt-studio
Prompt engineering workbench with a Lean persona layer that cuts LLM output size, cost, and latency. Injects the Lean ruleset every session via SessionStart + SubagentStart hooks.
decision-making
Master architectural decision-making: ADRs, technology selection, build-vs-buy analysis, proof of concepts, and migration planning.
claude-md-management
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.