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 skills/eveld/claude/spawn-research-agentsnpx skills add eveld/claude --skill spawn-research-agentsgit clone --depth 1 https://github.com/eveld/claudeWrote 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/eveld/claude/spawn-research-agents)<a href="https://agentmods.dev/skills/eveld/claude/spawn-research-agents"><img src="https://agentmods.dev/badge/skills/eveld/claude/spawn-research-agents.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00453 |
| Opus 5 | $0.00012 | $0.00227 |
| Sonnet 5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
spawn-research-agents 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 5d 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
Spawn Research Agents
Use specialized agents in parallel to research different aspects of the codebase efficiently.
Agent Selection
Choose agents based on research needs:
Always start with locators:
codebase-locator- Find WHERE files/components arethoughts-locator- Find WHAT documentation exists
Then use analyzers on findings:
codebase-analyzer- Understand HOW specific code workscodebase-pattern-finder- Find SIMILAR implementationsthoughts-analyzer- Extract insights from specific docs
Only if user explicitly requests:
web-search-researcher- External research
Parallel Execution Pattern
Spawn multiple agents at once using multiple Task calls in a single message:
Task(subagent_type="codebase-locator", prompt="Find all authentication files")
Task(subagent_type="thoughts-locator", prompt="Find auth-related documentation")
Then wait for both to complete before spawning follow-up agents.
Research Workflow
- Decompose: Break research question into specific areas
- Locate: Use locator agents to find relevant files/docs
- Analyze: Use analyzer agents on most promising findings
- Synthesize: Combine all results with file:line references
Example
Research question: "How does authentication work?"
Step 1 - Locate (parallel):
Task(subagent_type="codebase-locator", prompt="Find all authentication-related files including handlers, middleware, and services")
Task(subagent_type="thoughts-locator", prompt="Find any documentation about authentication implementation")
Step 2 - Analyze (parallel, after step 1 completes):
Task(subagent_type="codebase-analyzer", prompt="Analyze authentication flow from login endpoint through JWT generation")
Task(subagent_type="codebase-pattern-finder", prompt="Find examples of how other endpoints use authentication middleware")
Step 3 - Synthesize: Combine findings with specific file paths and line numbers.
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.
- 5d ago First seen · 62 lines · 23 tokens per session scan A c954a1aab03a
spawn-research-agents is a skill published in the GitHub repository eveld/claude (10 stars, last pushed 7mo ago), licensed MIT. It adds 23 tokens to every session and 453 once invoked, about $0.0001 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
code-indexing-pipeline
How Infigraph turns source into a graph — adding a language (tree-sitter vs ANTLR grammar-plugin), cross-file call resolution, SCIP compiler-grade enrichment, and file-watch/reindex triage. Use when adding language support, debugging unresolved calls or SCIP import, or triaging stale index/watcher issues.
analysis-subsystems
How Infigraph's multi-repo/group mode and taint analysis work internally — HTTP contract extraction heuristics, cross-service edge linking, combined-graph merge, remote mode, plus taint's line-based tracking and sanitizer heuristic. Use when working on crates/infigraph-core/src/multi/ or src/taint/, or investigating…
review-pr-against-issue
Review one or more PRs against the GitHub issue(s) they claim to fix, including fetching PR branches directly when gh can't reach github.com (e.g. gh is authenticated to an enterprise host instead). Use whenever asked "does this PR fix issue.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
specification-writing
Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.