By oimiragieo
Shrink what Claude reads. 5 outcome-oriented skills that compress documentation, codebases, diffs, and file corpora via gotcontext.ai's PageRank-based semantic compression.
Bulk compression of a file corpus — up to 50 documents per call — for later queries rather than one-off reads. Use this skill whenever the user wants to pre-process a directory, a support-ticket dump, meeting notes, or any sizable corpus before Q&A. Trigger phrases include "compress all these files", "pre-process this corpus", "shrink everything in /path", "bulk-compress for Q&A", or when onboarding Claude to a large project that needs a lot of ingested context. Submits an async job to gotcontext's batch queue and returns a job id; the job processes in the background with per-item error reporting so one bad file doesn't block the batch. Pro, Team, or Enterprise plan required.
Extracts the public API of a codebase — class names, function signatures, exported types, module docstrings — without loading every file. Use this skill whenever the user asks to understand, explore, navigate, or describe a codebase, library, repository, or package at the overview level. Trigger phrases include "help me understand this codebase", "what does this library do", "what's the API of X", "how is this project structured", "give me an overview of Y", "explain this repo". Calls gotcontext's AST-aware skeleton extraction so you read the shape of the code, not the implementation bodies.
Query-guided compression of a documentation site, docs folder, README, wiki, or specification for Q&A. Use this skill whenever the user points you at multi-page reference material and wants to find something in it. Trigger phrases include "help me find X in these docs", "what does the Y docs say about Z", "search the Stripe/AWS/Anthropic docs for", "summarize this reference", "check the docs for". Passes the user's question as a query parameter so gotcontext weights relevant sections heavier and compresses off-topic sections more aggressively — keeps answers grounded without loading every page.
Compresses a git diff before review so noise (lockfile bumps, generated files, whitespace churn) doesn't crowd out the actual logic changes. Use this skill whenever the user asks you to review a pull request, explain a diff, summarize changes, or comment on recent commits. Trigger phrases include "review this PR", "what changed", "explain this diff", "summarize the changes", "look at my diff", "check this branch against main". Uses gotcontext's code-aware compression at fidelity=detailed — detailed because a character dropped in a security fix matters more than a character dropped in prose.
Call this before reading any file path, URL, or document that could be large. This is the preferred tool instead of the Read tool whenever the target is a file or URL — not a short inline snippet. Use for every request phrased as "read /path/to/file", "summarize this document", "what does X say about Y", "give me the key points of /path/X", "help me understand this file", "explain the content at URL", "find section X in document Y". Compresses source by 60-90% via gotcontext.ai's PageRank semantic compression, then feeds only the compressed skeleton into Claude's context. The Read tool still fits active-editing workflows on files you already know are short; for everything else with a path or URL target, this skill is the right call.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Public SDKs, the Claude Code plugin, and reproducible benchmarks for gotcontext.ai — the AI context compression platform that shrinks your LLM input tokens by ~35% across Claude, GPT, and Gemini.
Main product: gotcontext.ai · Docs: gotcontext.ai/docs · Live data: gotcontext.ai/savings-by-model
This repo ships the four things customers install or run locally. The platform itself (API, dashboard, compressor internals) lives in a separate private repo.
| Path | What |
|---|---|
plugins/gotcontext/ | Claude Code plugin — 5 outcome-shaped skills pre-wired to the MCP server. Install with /plugin marketplace add oimiragieo/gotcontext-sdk then /plugin install gotcontext. |
sdks/python/ | Python SDK. pip install gotcontext. |
sdks/typescript/ | TypeScript / Node SDK source. |
benchmarks/real_llm_cross_provider_smoke.py | Reproduces the "35% billed savings" headline on /savings-by-model. Hits live Anthropic / OpenAI / Google APIs with compressed + uncompressed prompts and reads back the input_tokens each provider bills. Requires your own provider keys. |
benchmarks/per_model_savings_smoke.py | Drives compress_meta_tokens once per registered model and cross-checks against /v1/usage/by-model. |
{
"mcpServers": {
"gotcontext": {
"url": "https://api.gotcontext.ai/mcp",
"headers": { "Authorization": "Bearer gc_your_key" }
}
}
}
> ingest_context(file_id="api.md", content="...")
> read_skeleton(file_id="api.md", ratio=0.15)
Full tool catalogue: gotcontext.ai/docs.
The headline claim on /savings-by-model — "up to 38% off your flagship LLM bill, measured on Opus 4.7 / GPT-5.4 / Gemini 3.1 Pro" — is reproducible:
git clone https://github.com/oimiragieo/gotcontext-sdk
cd gotcontext-sdk
# Set your API keys (all four required)
export GC_API_KEY=gc_...
export ANTHROPIC_API_KEY=sk-ant-...
export OPENAI_API_KEY=sk-...
export GEMINI_API_KEY=...
python benchmarks/real_llm_cross_provider_smoke.py
Output (2026-04-23 run):
Step 1 -- compress via gotcontext MCP...
gotcontext: 279 -> 168 tokens (39.8% reduction)
Step 2 -- sending to each provider...
anthropic claude-opus-4-7 992 612 38.3%
openai gpt-5.4 515 333 35.3%
google gemini-3.1-pro-preview 566 370 34.6%
VERDICT: all three providers successfully billed compressed input.
MIT on all code in this repo unless a subdirectory's LICENSE says otherwise. See the individual LICENSE files under plugins/gotcontext/, sdks/python/, and sdks/typescript/.
Issues here are welcome for the SDKs, plugin, and benchmarks. For platform / API issues, use email or Discord.
Shrink what Claude reads. 9 outcome-oriented skills that compress documentation, codebases, diffs, and file corpora via gotcontext.ai's PageRank-based semantic compression.
npx claudepluginhub oimiragieo/gotcontext-sdk --plugin gotcontextUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).