godfetch
Unified external research for documentation, GitHub code, and package versions. Use when the user needs to look up library docs or API references, search code in a public GitHub repo, check the latest version of a package, verify whether a dependency is deprecated, or any task requiring external knowledge beyond the local codebase and training data.
How do I install this agent skill?
npx skills add https://github.com/trancong12102/agentskills --skill godfetchIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill provides a set of tools for technical research, including documentation discovery, code exploration, and package version checking. The analysis identified an indirect prompt injection surface and minor prompt instructions that discourage the agent from inspecting its own scripts. A security best-practice violation was also noted in a documentation probing script.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 2 issues
What does this agent skill do?
godfetch
Unified external research — look up library documentation, search source code in any git repository, and check package versions from a single skill.
Routing
| Intent | Primary tool | Fallback |
|---|---|---|
| Library docs, API reference | llms-probe → WebFetch llms.txt | context7 if no llms.txt published |
| Changelogs, breaking changes | llms-probe → WebFetch llms.txt | gh api contents for CHANGELOG.md |
| Cross-repo code search (exact identifier) | Sourcegraph MCP keyword_search | gh search code, then git-clone for follow-up |
| Semantic / concept query in a GitHub-hosted dep ("how does X work in lib Y") | mcp__plugin_ora_morph__github_codebase_search | git-clone if the question keeps branching across files |
| Concept query across multi-host or GitLab/Bitbucket repos | Sourcegraph MCP nls_search with 2-5 extracted keywords | keyword_search after picking a literal term |
| Deep dive in known repo (3+ files) | git-clone + shell tools | Sourcegraph read_file for one-off reads |
| GitHub issues | gh issue view <N> | gh search issues for discovery |
| GitHub PRs | gh pr view <N> | gh search prs for discovery |
| GitHub releases (versions, dates, notes) | gh release view <tag> --repo owner/repo | gh release list --repo owner/repo for browsing |
| Single file (known repo + path) | Sourcegraph MCP read_file | gh api repos/.../contents/<path> (GitHub only) |
| Symbol navigation (def, references) | Sourcegraph go_to_definition / find_references | git-clone + ast-grep |
| Git history / diff search across repos | Sourcegraph commit_search / diff_search / compare_revisions | gh api /repos/.../commits |
| Package version, deprecation | deps-dev | npm view for npm-only metadata |
| npm package info (non-version) | npm view <pkg> (Bash) | WebSearch for community sentiment |
| General web lookup | WebSearch → WebFetch | — |
| Comparison / decision | llms-probe per lib + WebSearch | context7 for additional snippets |
For mixed requests, launch all relevant tools in parallel. Probe and clone are I/O-bound — start them in the background and run WebFetch/context7/WebSearch concurrently to mask latency.
GitHub access rules
Do not use WebFetch on github.com or raw.githubusercontent.com URLs — use the right tool:
| GitHub content | Use | Never |
|---|---|---|
| Source code (exploration) | git-clone + shell tools | browsing files via gh api contents |
| Source file (known path) | gh api repos/.../contents/<path> | WebFetch raw.githubusercontent.com |
| Issues | gh issue view <N> --repo owner/repo | WebFetch github.com/.../issues/N |
| Pull requests | gh pr view <N> --repo owner/repo | WebFetch github.com/.../pull/N |
| Issue/PR search | gh search issues "q" --repo ... | WebFetch github.com/issues?q=... |
| Releases (versions, dates, notes) | gh release view/list --repo owner/repo or gh api repos/.../releases | WebFetch github.com/.../releases — relative timestamps on the HTML get hallucinated into training-era years |
| CHANGELOG.md | gh api repos/.../contents/CHANGELOG.md | WebFetch blob/ or raw URLs |
Search discipline
- deps-dev for versions: when checking latest version, deprecation, or comparing installed vs latest — always use
deps-devfirst. Only fall back tonpm viewor WebSearch if deps-dev errors or the package is private. - llms.txt first, context7 fallback: for library docs, run
scripts/llms-probe.shagainst the docs domain before reaching forcontext7. Author-published llms.txt has no community-curation lag and no enrichment layer that can hallucinate. Fall back tocontext7only when probe returns nothing.
llms.txt — Author-Canonical Library Documentation
Many doc sites publish llms.txt (Markdown index of doc pages) and llms-full.txt (concatenated full content). These are author-published — no enrichment layer, no community-curation lag — so they reflect the deployed docs version exactly. Prefer them over context7 when available.
Step 1: Probe for availability
bash scripts/llms-probe.sh <docs-domain>
Outputs TSV kind \t url \t size for any found files. Probes root + common nested paths (/docs/, /en/), follows redirects, dedupes. Returns non-zero exit if nothing found.
kind | Meaning |
|---|---|
| index | llms.txt — Markdown list of doc page URLs |
| full | llms-full.txt — entire docs corpus concatenated |
Size shows ? when the CDN strips both Content-Length and Content-Range headers (Vercel does this on react.dev) — treat ? as unknown and prefer the index path.
Step 2: Fetch based on what's there
| Found | Action |
|---|---|
llms-full.txt ≤ ~500 KB | WebFetch it directly — single round trip, full corpus |
llms-full.txt > ~500 KB or size ? | WebFetch llms.txt first, pick relevant section links, fetch those |
| Only index (no full) | WebFetch the index, then fetch individual page links |
| Probe failed | Fall back to context7 (next section) |
For multi-section pulls, dispatch the page WebFetch calls in parallel.
Known publishers
Confirmed live (April 2026): React (react.dev), Next.js (nextjs.org, content under /docs/), Vercel, Anthropic (docs.anthropic.com → platform.claude.com), Cloudflare (docs.cloudflare.com → developers.cloudflare.com), Supabase, Drizzle (orm.drizzle.team), Hono (hono.dev), Zod (zod.dev), Expo (docs.expo.dev), tRPC (trpc.io), shadcn/ui (ui.shadcn.com). Most Mintlify- and GitBook-hosted docs auto-publish.
Tailwind, most pre-1.0 libraries, and many community packages do not publish — those go straight to context7.
Rules
- Probe before assuming. Adoption is uneven and paths vary (root vs
/docs/vs redirects). Always runllms-probe.shand act on the TSV — never hardcode URLs. - Watch file size before fetching full. Cloudflare's
llms-full.txtis ~46 MB and Supabase reports?(chunked). A blind fetch of either blows the context window. The 500 KB threshold is a heuristic — adjust to remaining context budget. - Index → page chain for big corpora. Treat
llms.txtas a routing table: parse section headings, fetch only the page URLs that match the question.
context7 — Library Documentation (Fallback)
Reach for context7 when llms-probe.sh returns nothing — the library doesn't publish llms.txt, or its docs domain isn't reachable. Coverage spans ~33K libraries via community-curated indexes; tradeoff is an enrichment layer that can introduce inaccuracies the author-published llms.txt avoids.
Two-step workflow via the official ctx7 CLI. Requires bunx ctx7@latest login once (no API key env var).
Step 1: Resolve library ID
bunx ctx7@latest library <name> [query]
Lists library candidates with their Context7 IDs (e.g. /websites/react_dev), trust scores, and snippet counts. The optional [query] re-ranks results by relevance — pass it whenever you already know the topic. Add --json for machine-readable output.
Step 2: Fetch documentation
bunx ctx7@latest docs <libraryId> "<query>"
Returns markdown snippets ranked by relevance. Add --json for structured output. If the first answer is shallow or off-topic, retry with --research — it spins up sandboxed agents that read the source repo and run a live web search, at higher cost.
Rules:
- One-time setup:
bunx ctx7@latest login(interactive). Verify withbunx ctx7@latest whoami. - Always resolve the library ID first — IDs are not guessable.
- Write specific queries —
"useState hook with objects"beats"hooks". The query drives relevance ranking on both commands. - Use
--researchonly as a retry when the default answer was insufficient, not by default — it's slower and more expensive.
Reference: references/context7.md
Sourcegraph — Cross-Repo Search & Code Navigation (MCP)
Sourcegraph public instance exposes an HTTP MCP server at https://sourcegraph.com/.api/mcp providing 13+ tools for cross-repo search, code navigation, and git history. Configured in ora plugin's .mcp.json — tools auto-available to Clio.
Indexes 2M+ OSS repos across GitHub + GitLab + Bitbucket. Sub-second cross-repo queries, no local clone overhead.
Tools by intent:
| Intent | Tool |
|---|---|
| Search by exact identifier (AND) | keyword_search — literal match, ALL terms required. Filters: repo:, file:, lang:, rev: |
| Search by concept / vocab unknown | nls_search — OR logic + word stemming (handler matches handle). NOT semantic embedding |
| Read single file | read_file — 128KB cap; repo, path, optional revision / startLine / endLine |
| List directory | list_files |
| Find repos | list_repos |
| Symbol navigation | go_to_definition, find_references |
| Git history / diffs | commit_search, diff_search, compare_revisions |
| Contributor lookup | get_contributor_repos |
| AI synthesis over codebase | deepsearch — heavy; spawns subagents |
Rules:
- Pick
keyword_searchvsnls_searchby what you know. Concrete identifier (function/class/constant name, error string, literal phrase) →keyword_search. Vocab unknown / conceptual ("how does X work", cross-library pattern) →nls_search. Why:keyword_searchis AND + literal — missing one term zeroes the result;nls_searchis OR + stemming — broader recall but noisier ranking. - Extract keywords before
nls_search. Strip question words (how, what, where, does, is) and articles. Pass 2-5 meaningful nouns/verbs, not full sentences. Example: "how does the router match incoming requests" →router match request handler. Why: tool stems and OR-matches each term — natural-language fillers dilute the signal. - Scope with
repo:^...$anchors to avoid matching forks.repo:foo/barmatchesfoo/bar-forktoo;repo:^github\.com/foo/bar$does not. - Pattern: search → verify path →
read_file. When a search result is annotatedrepo@revision(e.g.github.com/foo/bar@abc123), split it and passrepo+revisionseparately toread_file. Omittingrevisionsilently reads HEAD of the default branch and may return different content. - Parallelize independent searches. Three repos to compare → fire three
keyword_search/nls_searchcalls in one message, not sequentially. - Discovery vs forensics —
keyword_search/nls_searchfor "find repos that…";git-clonefor tracing flow through 5+ files in one repo. - Index lag — Code published within the last ~24 hours may not be indexed. Fall back to
git-clone --refreshfor just-released versions. - Repo not indexed = fallback — If
read_filereturns null repository, drop togit-cloneorgh api contents. deepsearchis heavy — Spawns AI subagents. Use only whenkeyword_search+read_filecan't synthesize the answer and the target spans multiple repos or non-GitHub hosts. For GitHub-only synthesis usemcp__plugin_ora_morph__github_codebase_searchinstead — lighter and shaped for the same job.- Plan tier caveat — Sourcegraph docs note MCP access is part of Enterprise plans; public
sourcegraph.comMCP endpoint's free-tier behavior is unverified. If first tool call returns 401/403, drop togit-clone.
Reference: Sourcegraph MCP docs
Morph github_codebase_search — default for GitHub-hosted semantic queries
mcp__plugin_ora_morph__github_codebase_search runs Morph's WarpGrep subagent against a target public GitHub repo and returns a synthesized answer with file:line citations. Reach for it first when the question is shaped like "how does library X do Y", "where does package Z handle case W", "what's the data flow for feature V in repo R" — one morph call replaces a clone-then-grep-then-read loop.
- Use when the target repo is on GitHub and the question is conceptual / semantic ("how", "where", "what wires X to Y"). Why: morph parallelizes the per-file grep + read + synthesize the caller would otherwise do serially.
- Prefer Sourcegraph for: GitLab/Bitbucket targets, multi-repo cross-cutting searches, exact-identifier-with-filter queries (
repo:,lang:,rev:), git history / diffs. - Prefer
git-clonefor: 3+ files of follow-up exploration in one repo, ast-grep structural queries, or when the question keeps branching ("now show me where this is called, now show me the test for it"). - Trust citations, verify conclusions — morph's
file:linereferences point to real locations in the target repo, but its synthesis (what that code does, how it answers the question) can be wrong. When the answer is load-bearing, spot-check viagh api repos/.../contents/<path>orgit-clone+ Read.
git-clone — Source Code Exploration
Shallow-clone any public git repo into a local cache and explore the working tree with shell tools. Cache lives at ~/.cache/clio-repos/ and is reused across sessions.
bash scripts/git-clone.sh <repo> [--branch X] [--refresh]
The script echoes the absolute path of the cached clone. Subsequent calls for the same repo return the cached path instantly (no re-clone).
Repo argument forms:
owner/repo— GitHub shortcut (e.g.vercel/next.js)- Full HTTPS URL — works for any host (
https://gitlab.com/...,https://gitlab.jmango360.com/...) - SSH form —
git@host:path(requires SSH key configured)
Parallelization: clone is I/O-bound (1-3s for small/medium repos). When researching a topic that needs both docs and source code, dispatch the clone and llms-probe/context7/WebSearch in parallel — by the time docs return, the clone is ready to explore.
Rules:
- Do not read script source code. Run with
--helpfor usage. - Default cache is
~/.cache/clio-repos/; override with--cache-dirwhen needed. - Caches are reused — pass
--refreshonly when you need the latest commit. - For one-off file fetches by exact path, prefer
gh api repos/.../contents/<path>— no clone overhead.
deps-dev — Package Versions
Query latest stable versions from public registries. No API key needed.
python3 scripts/get-versions.py <system> <pkg1> [pkg2] ...
Supported ecosystems:
| Ecosystem | System ID | Example |
|---|---|---|
| npm | npm | express, @types/node |
| PyPI | pypi | requests, django |
| Go | go | github.com/gin-gonic/gin |
| Cargo | cargo | serde, tokio |
| Maven | maven | org.springframework:spring-core |
| NuGet | nuget | Newtonsoft.Json |
| RubyGems | rubygems | rails, sidekiq |
Output: TSV with columns package, version, published, status.
Rules:
- Do not read script source code. Run directly or use
--help. - Batch lookups when possible — pass multiple package names in one call.
- Flag deprecated packages — if status says
deprecated, suggest an alternative.
Reference: references/deps-dev.md
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/trancong12102/agentskills/godfetch">View godfetch on skillZs</a>