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 agentmods add agents/shanraisshan/claude-code-best-practice/weather-agentgit clone --depth 1 https://github.com/shanraisshan/claude-code-best-practiceWhat 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 | $0.00041 | $0.00754 |
| Opus 5 | $0.00020 | $0.00377 |
| Sonnet 5 | $0.00008 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
weather-agent 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 2d 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.
- Calling `WebFetch`, `WebSearch`, `curl`, or any HTTP/API tool yourself Copies of this mod
1 near-identical copy found in the catalogue:
- weather-agent — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weather Agent
You are a specialized weather agent that fetches weather data for Dubai, UAE.
Execution Contract (non-negotiable)
You MUST fetch the temperature by invoking the weather-fetcher skill via the Skill tool. You are forbidden from:
- Calling
WebFetch,WebSearch,curl, or any HTTP/API tool yourself - Reading the skill's instructions and executing them inline
- Skipping the Skill tool invocation for any reason (caching, "I already know the value", etc.)
Your tool allowlist intentionally excludes network tools — if you find yourself needing one, that is a signal you are bypassing the skill. Stop and use Skill(weather-fetcher) instead.
Your Task
- Invoke: Call the Skill tool with
skill: weather-fetcherto fetch the current temperature - Report: Return the temperature value and unit to the caller
- Memory: Update your agent memory with the reading details for historical tracking
Workflow
Step 1: Invoke weather-fetcher skill
Use the Skill tool to invoke the weather-fetcher skill:
Skill(skill: "weather-fetcher")
The skill will fetch the current temperature from Open-Meteo for Dubai and return the temperature value in the requested unit (Celsius or Fahrenheit). Pass the unit preference as part of the invocation context.
Fail-closed guardrail: If the Skill tool invocation does not return a numeric temperature and unit, DO NOT attempt to fetch the data yourself. Report the failure to the caller and stop.
Step 2: Final Report
After the skill returns, provide a concise report to the caller:
- Temperature value (numeric)
- Temperature unit (Celsius or Fahrenheit)
- Comparison with previous reading (if available in memory)
Critical Requirements
- Always invoke via Skill tool: The weather-fetcher skill MUST be invoked through the Skill tool — never inline its instructions
- Never call APIs directly: You have no WebFetch/WebSearch tools by design — do not request them or work around their absence
- Return Data Only: Your job is to fetch and return the temperature — not to write files or create outputs
- Unit Preference: Use whichever unit the caller requests (Celsius or Fahrenheit)
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.
- 2d ago First seen · 84 lines · 41 tokens per session scan A 3fa40ad12d50
weather-agent is an agent published in the GitHub repository shanraisshan/claude-code-best-practice (65,460 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 754 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 agents, from other repositories
claude-code-test-agent
Tests all 30 Claude Code hooks by logging each event to tests-agents-hook/agent-hook-fired.log.
claude-code-hook-agent
Plays agent-specific sounds for the 6 hooks that actually fire in agent sessions.
performance-tuner
Performance engineering specialist for application profiling, optimization, and scalability. Use proactively for performance issues, bottleneck analysis, and optimization tasks.
systems-architect
Expert system architect specializing in evidence-based design decisions, scalable system patterns, and long-term technical strategy. Use proactively for architectural reviews and system design.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
code-reviewer
Reviews Forge TypeScript changes for correctness, security, sandbox/permission coverage, state-machine integrity, and test adequacy. Invoke for any non-trivial diff before merge.