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/d-o-hub/github-template-ai-agents/do-web-doc-resolvernpx skills add d-o-hub/github-template-ai-agents --skill do-web-doc-resolvergit clone --depth 1 https://github.com/d-o-hub/github-template-ai-agentsWrote 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/d-o-hub/github-template-ai-agents/do-web-doc-resolver)<a href="https://agentmods.dev/skills/d-o-hub/github-template-ai-agents/do-web-doc-resolver"><img src="https://agentmods.dev/badge/skills/d-o-hub/github-template-ai-agents/do-web-doc-resolver.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 | $0.00094 | $0.01453 |
| Opus 5 | $0.00047 | $0.00727 |
| Sonnet 5 | $0.00019 | $0.00291 |
| Haiku 4.5 | $0.00009 | $0.00145 |
Grade A, and why
do-web-doc-resolver 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Doc Resolver Skill
Resolve URLs and queries into compact, LLM-ready markdown using a progressive, free-first cascade with 2026 production patterns.
When to Use
- Fetch and parse documentation from a URL
- Search for technical information across the web
- Build context from web sources for AI agents
- Validate content against agent-docs-spec v0.3.0
- Trace resolution trajectories for debugging
Quick Start
python -m scripts.resolve "https://docs.rust-lang.org/book/"
python -m scripts.resolve "Rust async programming" --profile quality --trace --json
Cascade Strategy
URL: Cache → llms.txt → Jina → Direct Fetch → Firecrawl → Mistral Browser → DuckDuckGo
Query: Cache → Exa MCP → Exa SDK → Tavily → Serper → DuckDuckGo → Mistral Web Search
Providers (12 total)
| Provider | Type | Free | Latency |
|---|---|---|---|
llms_txt |
URL | Yes | ~100ms |
jina |
URL | Yes | ~300-1500ms |
exa_mcp |
Query | Yes | Varies |
duckduckgo |
Query | Yes | ~2s |
direct_fetch |
URL | Yes | ~500ms |
exa, tavily, serper |
Query | No | ~1s |
firecrawl, mistral_* |
URL/Query | No | ~2-3s |
docling, ocr |
URL | No | ~3-5s |
Execution Profiles
| Profile | Attempts | Paid | Latency | Quality |
|---|---|---|---|---|
free |
3 | 0 | 6s | 0.70 |
fast |
2 | 1 | 4s | 0.60 |
balanced |
4-6 | 1-2 | 9-12s | 0.65 |
quality |
6-10 | 3-5 | 15-20s | 0.55 |
Key Features
Structured Tool Contracts: Every provider returns ProviderResult(ok, content, error, meta) with ProviderMeta(tool, duration_ms, cache_hit, quality_score, error_type).
Layered Routing Memory: TTL-based decay (30 days), metadata filtering, recency weighting. See scripts/routing_memory.py.
Trace-Based Evaluation: Emit ResolutionTrace with TraceStep per provider. CLI: --trace --json.
Agent-Friendly Docs Validation: Validates against agent-docs-spec v0.3.0 — 10 checks across 7 categories.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- __init__.py 197 B runs code
- __main__.py 68 B runs code
- .env.example 252 B
- .gitignore 131 B
- evals/evals.json 1.8 KB
- pyproject.toml 3.9 KB
- references/CASCADE.md 6.6 KB
- references/CLI.md 5.1 KB
- references/CONFIG.md 4.9 KB
- references/PROVIDERS.md 5.2 KB
- references/RUST_CLI.md 7.1 KB
- references/TESTING.md 7.0 KB
- references/web-research-optimization.md 12 KB
- requirements.txt 275 B
- scripts/__init__.py 0 B runs code
- scripts/_cascade_async.py 8.1 KB runs code
- scripts/_cascade.py 8.1 KB runs code
- scripts/_query_resolve.py 4.5 KB runs code
- scripts/_routing_utils.py 364 B runs code
- scripts/_url_resolve_async.py 6.9 KB runs code
- scripts/_url_resolve.py 6.7 KB runs code
- scripts/cache_negative.py 2.1 KB runs code
- scripts/capture/capture-flow.sh 2.2 KB runs code
- scripts/capture/capture-release.sh 1.6 KB runs code
- scripts/capture/capture-responsive.sh 1.1 KB runs code
- scripts/circuit_breaker.py 2.4 KB runs code
- scripts/cli.py 3.3 KB runs code
- scripts/constants.py 4.0 KB runs code
- scripts/diagnose_providers.py 4.3 KB runs code
- scripts/docs_validation.py 7.9 KB runs code
- scripts/models.py 5.5 KB runs code
- scripts/provider_decorator.py 3.1 KB runs code
- scripts/providers_impl.py 1.3 KB runs code
- scripts/providers/__init__.py 2.0 KB runs code
- scripts/providers/docling.py 3.4 KB runs code
- scripts/providers/duckduckgo.py 2.7 KB runs code
- scripts/providers/exa.py 8.2 KB runs code
- scripts/providers/firecrawl.py 4.2 KB runs code
- scripts/providers/jina.py 3.8 KB runs code
- scripts/providers/mistral.py 12 KB runs code
- scripts/providers/serper.py 5.1 KB runs code
- scripts/providers/stealth.py 945 B runs code
- scripts/providers/tavily.py 3.8 KB runs code
- scripts/providers/visual_clip.py 3.4 KB runs code
- scripts/quality.py 5.5 KB runs code
- scripts/resolve.py 7.8 KB runs code
- scripts/routing_memory.py 4.4 KB runs code
- scripts/routing.py 7.1 KB runs code
- scripts/semantic_cache.py 16 KB runs code
- scripts/state.py 652 B runs code
- scripts/synthesis.py 8.8 KB runs code
- scripts/utils/__init__.py 4.2 KB runs code
- scripts/utils/async_http.py 7.7 KB runs code
- scripts/utils/cache.py 3.4 KB runs code
- scripts/utils/content_clean.py 2.5 KB runs code
- scripts/utils/fetch.py 3.7 KB runs code
- scripts/utils/html.py 4.1 KB runs code
- scripts/utils/http.py 8.6 KB runs code
- scripts/utils/thread_pool.py 1.0 KB runs code
- scripts/utils/urls.py 3.8 KB runs code
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 · 139 lines · 94 tokens per session scan A cc5a2a8edd3a
do-web-doc-resolver is a skill published in the GitHub repository d-o-hub/github-template-ai-agents (2 stars, last pushed 2d ago), licensed MIT. It adds 94 tokens to every session and 1,453 once invoked, about $0.0005 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
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.
golden-rss
Use when testing the rss golden build.
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…
omh-rust
This is a Hermes-native rust workflow skill.