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 mdsakalu/agent-plugins --skill suggesting-skillsgit clone --depth 1 https://github.com/mdsakalu/agent-pluginsWrote 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/mdsakalu/agent-plugins/suggesting-skills)<a href="https://agentmods.dev/skills/mdsakalu/agent-plugins/suggesting-skills"><img src="https://agentmods.dev/badge/skills/mdsakalu/agent-plugins/suggesting-skills/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/mdsakalu/agent-plugins/suggesting-skills"><img src="https://agentmods.dev/badge/skills/mdsakalu/agent-plugins/suggesting-skills.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 | $0.00056 | $0.01684 |
| Opus 5 | $0.00028 | $0.00842 |
| Sonnet 5 | $0.00011 | $0.00337 |
| Haiku 4.5 | $0.00006 | $0.00168 |
Grade A, and why
suggesting-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 9d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suggesting Skills
Analyzes Claude Code sessions to identify opportunities for new skills based on:
- Repeated patterns that could be codified
- Complex multi-step workflows done manually
- External tool integrations that could be standardized
- Tasks requiring significant back-and-forth that could be streamlined
Storage Location
All suggestions are saved to: ~/.claude/skill-suggestions/
Each suggestion is a separate markdown file with timestamp to avoid conflicts:
~/.claude/skill-suggestions/
├── 2026-01-15-143052-api-testing.md
├── 2026-01-15-160823-log-analysis.md
└── ...
Commands
/suggest-skills - Analyze Current Session
When invoked, analyze the current session for skill opportunities.
Analysis Criteria:
-
Repeated Patterns - Look for tasks done multiple times with similar structure
- Same sequence of tool calls repeated
- Similar prompts asking for the same type of work
- Copy-paste patterns that could be templated
-
Complex Workflows - Multi-step processes that could be codified
- Tasks requiring 5+ sequential steps
- Workflows with conditional logic or decision points
- Processes that required user clarification mid-stream
-
Tool Integrations - External tools or APIs used that could be standardized
- CLI tools with complex flag combinations
- API calls with specific patterns
- Data transformations or parsing
-
Pain Points - Areas where the session struggled
- Multiple attempts to get something right
- Errors that required recovery steps
- Tasks where instructions were unclear
Suggestion Format:
For each potential skill identified, save a file to ~/.claude/skill-suggestions/ with:
# Skill Suggestion: [Name]
**Generated:** [timestamp]
**Session Context:** [brief description of what was being worked on]
## Observed Pattern
[Description of what was observed in the session]
## Proposed Skill
**Name:** [suggested-skill-name]
**Description:** [one-line description]
### What It Would Do
[2-3 sentences explaining the skill's purpose]
### Example Usage
[Example of how a user would invoke/use this skill]
### Key Components
- [Component 1]
- [Component 2]
- ...
## Evidence From Session
[Specific examples from the session that support this suggestion]
## Implementation Notes
[Any technical considerations for implementing this skill]
---
Status: pending
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.
- 9d ago First seen · 237 lines · 56 tokens per session scan A 0e5742f402a4
suggesting-skills is a skill published in the GitHub repository mdsakalu/agent-plugins (4 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,684 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…