Token-efficient symbolic encoding
Compression of context/output. rtk-token-killer's PreToolUse Bash intercept won the field.
5 primary frameworks · 9 lower-confidence entries
Keeps raw tool output data out of the context window via sandbox execution and SQLite+FTS5 session indexing, reducing context consumption by up to 98% while…
A full-session context runtime that compresses file reads (10 modes), shell output (60+ patterns), and session memory (CCP) to save 60-99% of tokens while…
Persists AI agent context across sessions as 100%-local plain JSON files with zero dependencies, zero cloud, and agent identity attribution.
Provides AI coding agents with typed semantic memory, tree-sitter code intelligence, and a multi-agent coordination protocol to save 80-200K+ tokens per…
Lean/Verbose dual-mode Agent OS fork for solo developers on token budgets.
Show 9 lower-confidence entriestier-b · tier-c · unknown · delta reports
These entries map to § a19 by tag but carry weaker evidence — fewer documented primitives, delta reports of absent skills, or marketing-only sites without a public repo. They're listed for completeness; treat them with appropriate caution.
Intercepts Claude Code's Bash tool calls at the PreToolUse hook and compresses verbose CLI output (git status, test runners, builds) by 60-90% before it enters …
Replaces traditional tool-calling with TypeScript code execution in a sandbox, collapsing N sequential tool calls into 1 code execution with all registered tool…
Token-efficient multi-plugin engineering kit with automatic adversarial self-reflection and granular plugin installs.
Compresses the entire SDD workflow into a single SPEC.md file using caveman encoding (~75% fewer tokens) with automatic bug-to-invariant backpropagation on test…
Curated multi-plugin marketplace for SW engineering workflows with optional token-efficient code execution runtime for bulk file operations.
Token-efficient re-implementation of BMAD-METHOD using Claude Code's native skill-md format with 3 lifecycle hooks and a project-level taxonomy for workflow rou…
Give AI agents persistent architectural orientation by reverse-engineering OpenSpec living specs from code and exposing the graph via 45 MCP tools, reducing per…
28 MCP servers providing schema-validated JSON output for 240 developer tools, eliminating ANSI escape codes and fragile CLI output parsing with 36-95% token re…
Reduce AI agent token consumption by 96–98% on git/npm/brew operations by acting as a deterministic command broker that returns structured MCP payloads instead …