headroom
01Plugin Claude Code
Headroom startup hooks for Claude Code and GitHub Copilot CLI.
22 tagged context-window, measured the same way as everything else here.
Browse within: claude-code-plugin 6
Plugin Claude Code
Headroom startup hooks for Claude Code and GitHub Copilot CLI.
Plugin Claude Code
Token-efficient retrieval MCP servers for code, docs, and tabular data.
Plugin Claude Code
Bundles 6 skills, 2 commands, 1 plugin · 290 tokens together
Audit, fix, and monitor Claude Code context window usage. Find the ghost tokens.
Plugin Claude Code
Bundles 1 skill, 5 commands, 5 hooks · 135 tokens together
Governor: always-on compact professional output, telemetry, context slimming, tool-output filtering, prompt guidance, and drift guardrails for Claude Code Max users.
Plugin Claude Code
Bundles 1 skill, 7 commands, 3 hooks, 2 MCP servers · 250 tokens together
Linggen for Claude Code — two local MCP servers, each tool served in one place: durable cross-host memory from ling-mem, browser control in your own Chrome and logged-in X reads from the Linggen engine. Per-turn memory recall built in, and /linggen:config points this host at a Linggen on another machine. Installs its…
Plugin Claude Code
Bundles 2 skills · 104 tokens together
Measures what share of your agent's loaded context is ever actually invoked - skills, MCP servers, subagents, hooks, always-loaded prose - using evidence from your own session transcripts. Then prunes the dead weight, reversibly.
Plugin Claude Code
Bundles 4 skills, 1 MCP server · 381 tokens together
Compress tool responses and keep explicitly indexed output searchable without flooding the agent context window.
Plugin Claude Code
Bundles 1 skill · 179 tokens together
Route every coding task to the most token-efficient tool per layer: serena (code reads), rtk (command output), caveman (prose output), Ponytail (code output) — backed by a 9-tool benchmark.
Plugin Claude Code
Bundles 1 command · 20 tokens together
A lightweight Claude Code status bar that shows live details such as context, token use, balance, current tasks, tools, agents, cost, Git, estimated time, and warnings. It includes 21 display themes and has no runtime dependencies.
Plugin Claude Code
Context compression and persistent retrieval for Claude Code.
Plugin Claude Code
Bundles 27 skills · 808 tokens together
Secure memory + persistent context + skill-admission gate for Claude Code. HMAC-chained toolcalls + outcomes, per-agent HKDF subkey isolation, Postgres RLS, work-stealing task queue, MemGPT-style persistent memory, Agent Notebook Model (Read→Summary redirect), and v0.26.0+ Anthropic-style filesystem skills with AST.
Plugin Claude Code
Bundles 2 skills · 208 tokens together
Context budget and session continuity for Claude Code: HANDOFF checkpoints, resume, statusline.
Plugin Claude Code
Bundles 3 skills, 25 agents, 5 hooks, 1 MCP server · 1,770 tokens together
Saves 60-90% tokens on AI code reading. AST-aware lazy reads, symbol navigation, findusages, structural git diff/log, edit-safety guard, Task-routing matcher, cross-session telemetry (errors + diagnostics), 25 tp- subagents tiered to haiku/sonnet/opus with budget watchdog.
Plugin Claude Code
Bundles 3 skills, 3 hooks · 232 tokens together
Quiets noisy Bash commands (JS/npm, Python, JVM/Scala, Go, Rust, Ruby, make, docker, bazel, big git diffs) by redirecting full output to a temp log and surfacing only a summary — saving context tokens while preserving failure details.
Plugin Claude Code
Automatically compress large natural text or log files before processing using LLMLingua to save tokens. Trigger when the user pastes massive text blobs, asks to analyze a large file (logs, docs, transcripts), or provides a prompt too large for the context window.
Plugin Claude Code
Bundles 1 skill, 1 command, 2 agents, 7 hooks · 150 tokens together
A scrim between the tool and the model. Cost observability and tool-output thinning for Claude Code and Codex. Local, fail-open.
msiShariful/claude-token-inspector
Plugin Claude Code
Claude Code plugins by Shariful Islam — token inspection and context optimization tools.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 81 tokens together
Skills and MCP server for context optimization — decide whether compressing an agent's context pays for the prompt cache it invalidates, and compress it when the answer is yes. Bundles the distil MCP server so install wires everything in one step.
Plugin Claude Code
Bundles 1 skill, 2 commands · 67 tokens together
Compress documentation, prompts, and context into minimal tokens for AGENTS.md. Based on Vercel's research showing compressed passive context achieves 100% pass rate vs 53% baseline.
Plugin Claude Code
Working-memory shelf for Claude Code: the /shelve skill plus a SessionStart hook that injects the shelf INDEX (recall bootstrap) and a SessionEnd/PreCompact hook that pushes the shelf so episodes survive an ephemeral container.
Plugin Claude Code
Bundles 5 skills, 1 MCP server · 0 tokens together
Protects your AI context window via sandboxed execution and smart indexing.
Plugin Claude Code
Use many MCP servers without context bloat. Winnow hides all your MCP servers behind one gateway exposing just 4 tools (searchtools / loadtool / calltool / runcode), so the model spends a fraction of the context.