Borrowing it
Nothing to install: this file belongs to ccivlcid/VibeHarness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ccivlcid/VibeHarness/main/.claude/commands/web-research.mdgit clone --depth 1 https://github.com/ccivlcid/VibeHarnessWrote 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/commands/ccivlcid/vibeharness/web-research)<a href="https://agentmods.dev/commands/ccivlcid/vibeharness/web-research"><img src="https://agentmods.dev/badge/commands/ccivlcid/vibeharness/web-research.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 5.1 | $0.00000 | $0.00441 |
| Opus 5 | $0.00000 | $0.00220 |
| Sonnet 5 | $0.00000 | $0.00088 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
web-research 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 6d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research — Don't Guess, Search
This command is part of the VibeHarness framework.
Core principle: Don't guess. If you're not sure, search.
Building on wrong information means rebuilding everything later. 5 minutes of research prevents 5 hours of rework.
When to Search
During Planning
- Ideas requiring external API/service integration (stock/crypto trading, maps, payments, social media, weather, etc.)
- Ideas with domain-specific rules/constraints (finance, healthcare, legal, etc.)
- Checking what tech similar services use
During Development
- Latest docs, endpoints, and auth methods for APIs you're using
- Latest library/framework versions and breaking changes
- Best practices for specific feature implementations
During Error Resolution
- Unfamiliar error messages
- Library compatibility issues
- Environment configuration problems
What to Search For
| Situation | Search For |
|---|---|
| External API integration | API docs, free/paid tiers, rate limits, auth method |
| Domain-specific rules | Legal constraints, requirements, licenses |
| Tech selection | Comparison articles, benchmarks, pros/cons, community size |
| Error resolution | Error message + environment info |
| Latest versions | Official docs, release notes, migration guides |
Using Search Results
Always reflect search results in documentation:
In planning docs:
- "This exchange API allows 1,000 free calls per month"
- "The Maps API requires signing up and getting a key"
- "Auto-trading is legal but there are financial regulations to be aware of"
In technical decision docs:
- API documentation URLs found via search
- Version differences
- Known constraints
For non-developers:
- Only share what they need to know, in simple terms
- "To build this feature, you'll need to sign up at ~. It's free/paid"
When NOT to Search
- Well-known fundamentals (HTML, CSS, basic JavaScript syntax)
- Questions about the project's own code (just read the code)
- Topics already researched and recorded in docs/ai-dev/ from a previous session
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.
- 6d ago First seen · 60 lines · 0 tokens per session scan A 1987b41f5888
web-research is a command published in the GitHub repository ccivlcid/VibeHarness (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 441 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.