search-budget-policy
Skill0 starsChanged 5 months agoMITView on GitHub
Route web lookups across Brave, Tavily, Scrapling, and DuckDuckGo while conserving paid API quota.
In this repository17 other files it gives its agents.
- community-marketingSkill
- copywritingSkill
- social-contentSkill
- memory-dreamSkill
- memory-triageSkill
- skill-vetterSkill
- apple_mail_salesSkill
- company_brainSkill
- lead_handoffSkill
- scrapling-lead-searchSkill
- market-environment-analysisSkill
- stock-analysisSkill
- us-stock-radarSkill
- Agent BrowserSkill
- find-skillsSkill
- githubSkill
- summarizeSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. About 0 are common, 13 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈13
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Use this 4-level search order:
- Distinctive: line 11
Use when source quality and freshness matter.
- Very specific: line 16
If web_search already hit a Scrapling provider failure for the same query/error, skip duplicate retries and move to level 2 or 4 as …
- Distinctive: line 26
Use when higher-priority paths are unavailable.
- Distinctive: line 31
Do NOT use paid search for simple definitions, translation, rewriting, or summarization.
- Distinctive: line 32
Do NOT repeat nearly identical queries.
- Distinctive: line 34
If a path fails once for the same query, move to the next fallback level instead of retry looping.
- Distinctive: line 35
Keep retries bounded (max 3 with short backoff).
- Very specific: line 37
When to use built-in web_search (primary):
- Very specific: line 44
When to use tavily_search:
- Very specific: line 48
If web_search already failed for the same query/error, do not loop.
- Distinctive: line 55
When to use DDG fallback:
- Very specific: line 61
Use web_fetch only after you already have a target URL from search results or the user gave you a URL.
- Distinctive: line 62
Do not fetch many pages speculatively.
- Distinctive: line 63
Prefer fetching 1 page first, then expand only if needed.
- Distinctive: line 68
If the answer does not require live web access, answer directly without any search.
- Distinctive: line 69
If paid search is not justified, prefer lower-cost fallback or no search.
- Distinctive: line 70
If all search methods appear unavailable, stop wasting calls and answer from available context, clearly stating the limitation.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Use this 4-level search order:
- Built-in
web_search(configured provider, currently Scrapling via Brave web/API fallback)- Primary path for high-value lookups.
- Use when source quality and freshness matter.
tavily_search- Secondary path when primary search fails, rate-limits, or has weak recall.
- Good structured backup for research tasks.
- If
web_searchalready hit a Scrapling provider failure for the same query/error, skip duplicate retries and move to level 2 or 4 as appropriate.
scrapling-lead-search(no API fallback)- Third path for resilient low-cost recovery when provider tools are flaky.
- General web/news queries should disable the lead-only intent filter:
python3 skills/growth/scrapling-lead-search/tools/scrapling_lead_search.py --query "<query>" --max-results 10 --no-api-fallback --skip-intent-filter --json - Lead discovery can keep the original default filter.
- DuckDuckGo fallback (
ddg-search/github-ddgr-search)- Last-resort path only.
- Use when higher-priority paths are unavailable.
Search budgeting policy:
- Assume paid providers have limited quota and should be preserved.
- Behave conservatively:
- Do NOT use paid search for simple definitions, translation, rewriting, or summarization.
- Do NOT repeat nearly identical queries.
- Reuse prior search results whenever possible.
- If a path fails once for the same query, move to the next fallback level instead of retry looping.
- Keep retries bounded (max 3 with short backoff).
When to use built-in web_search (primary):
- User explicitly asks to search the web
- User needs the latest/current information
- Official source discovery matters
- Commercial or business research quality matters
- You need authoritative first-pass results
When to use tavily_search:
- Primary Scrapling-backed
web_searchfailed in this session - You still need structured API results
- You need a second high-quality source without dropping to DDG yet
- If
web_searchalready failed for the same query/error, do not loop; move to the next fallback
When to use scrapling-lead-search:
- Provider tools are unstable
- You need resilient lead discovery with minimal paid API burn
- You want low-cost web HTML discovery before API fallback
When to use DDG fallback:
- Primary/Tavily/Scrapling paths all failed
- Query is exploratory/lower-stakes
- You only need rough candidate URLs
web_fetch policy:
- Use
web_fetchonly after you already have a target URL from search results or the user gave you a URL. - Do not fetch many pages speculatively.
- Prefer fetching 1 page first, then expand only if needed.
- Remember:
web_fetchdoes plain HTTP fetch and readable extraction, not JavaScript rendering. - For JS-heavy or login-protected pages, prefer the Browser tool instead.
Response behavior:
- If the answer does not require live web access, answer directly without any search.
- If paid search is not justified, prefer lower-cost fallback or no search.
- If all search methods appear unavailable, stop wasting calls and answer from available context, clearly stating the limitation.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

