context engineering plugins

183 tagged context engineering, measured the same way as everything else here.

Browse within: agent-memory 17agentic 11ai-memory 10knowledge-management 10ai-driven-development 8commands 8claude-agent 7context-design 7hooks 7prompt-engineering 7spec-driven-development 7claude-code-skill 6context 6context-management 6

token-master

122

All-The-Vibes/TokenMasterX

Plugin Claude Code

Token-efficient code-understanding harness. Routes structural questions (callers, callees, impact, inheritors) to a prebuilt code graph instead of repeated grep and file-reads, cutting cumulative context tokens. Type /token-master in a repo to build the index and turn on routing.

3 24d ago A tokens not measured original MIT

loop-contract

124

hdkhosravian/loop-contract-skill

Plugin Claude Code

Turns a rough, long-running request into a loop-engineered contract and then executes it — frozen scope counted from the source, an achievement oracle written red before the work, a distinct proof per item, and a completion gate that runs the oracle itself so "done" is a fact rather than a claim.

3 20d ago A tokens not measured original MIT

repomemory

125

DanielGuru/repomemory

Plugin Claude Code

Persistent, structured memory for AI coding agents. Your codebase never forgets. Hybrid keyword + semantic search, auto-session capture, intelligent category routing.

2 4mo ago A tokens not measured original MIT

promptsmith

126

emtcmca/promptsmith

Plugin Claude Code

Plugin marketplace listing 1 plugin: promptsmith.

2 1mo ago A tokens not measured original Apache-2.0

promptsmith

127

emtcmca/promptsmith

Plugin Claude Code

Prompt & context engineering for agents — /sharpen rough requests, /forge-agent reusable system prompts, /lens to review through expert lenses (or grade a prompt against a rubric with --grade), and /orchestrate multi-domain builds across a 20-agent specialist gallery. Eval-backed. Zero dependencies, no API keys, model.

2 1mo ago A tokens not measured original Apache-2.0

scorekeeper

129

michalstrnadel/scorekeeper

Plugin Claude Code

Commitment tracking for LLM agents — a deontic scoreboard of what the agent is entitled to claim and to do; catches drift and overreach.

2 1mo ago A tokens not measured original Apache-2.0

cardio

130

johanes/drydocs

Plugin Claude Code

Slim your CLAUDE.md into a lean index; move the detail into a well-organized docs/ folder that loads on demand (MOC + PARA + Zettelkasten). Non-destructive, idempotent, git-reversible.

2 1mo ago A tokens not measured original MIT

drydocs

131

johanes/drydocs

Plugin Claude Code

Slim your CLAUDE.md into a lean index by extracting detail into a well-organized docs/ folder, using MOC + PARA + Zettelkasten. Idempotent, git-reversible, non-destructive.

2 1mo ago A tokens not measured original MIT

cutweight

132

brenbuilds1/cutweight

Plugin Claude Code

Plugin marketplace listing 1 plugin: cutweight.

2 1mo ago A tokens not measured original MIT

cutweight

133

brenbuilds1/cutweight

Plugin Claude Code

Cut your agent's token weight: weigh in, read the bill, cut the output, cap the thinking, keep sessions lean.

2 1mo ago A tokens not measured original MIT

auto-pilot

135

IronRookieCoder/auto-pilot

Plugin Claude Code

Long-cycle coding workflow plugin - Structured state machine with TDD-driven milestone execution and deterministic gates for sustained AI coding sessions.

2 4mo ago A tokens not measured

claude-amber

136

yanfeid/claude-amber

Plugin Claude Code

Amber — zero-dependency context survival kit for Claude Code.

2 2mo ago A tokens not measured original MIT

amber

137

yanfeid/claude-amber

Plugin Claude Code

Zero-dependency context survival kit for Claude Code. Auto-checkpoints your session state to plain Markdown before compaction, restores it after — plus focus skills that keep Claude lean and on-task. No database, no background process, no AI compression. Just files you can read.

2 2mo ago A tokens not measured original MIT

llm-language

139

Silence-view/llm-language

Plugin Claude Code

Self-evolving prompt meta-compiler for the Fable 5 / Opus 4.8 era (Mythos-class aware) with xhigh/max effort, adaptive thinking, task budgets, dual-layer memory (ROSETTA.md + auto-memory), AND skill-level meta-refinement. v4.4: FABLE-5-ERA RETARGET — complexity map gains a model dimension (Opus 4.8 workhorse default…

2 2mo ago A tokens not measured original MIT

agenisea-ai

140

agenisea/turing

Plugin Claude Code

Plugin marketplace listing 1 plugin: turing.

2 7mo ago A tokens not measured original MIT

turing

141

agenisea/turing

Plugin Claude Code

Autonomous state machine for cognitive continuity. Preserves session state before context compaction and restores it on session start. Features priority-based selective restore, token budget tracking, auto decision extraction, and state archiving. Based on Alan Turing's 1936 paper 'On Computable Numbers'.

2 7mo ago A tokens not measured original MIT

koshi

142

jsharma1105/Koshi

Plugin Claude Code

Koshi MCP — retrieval, context engineering, persistent memory, and quality scoring for AI agents. 100% offline.

2 11d ago A tokens not measured original MIT

dev-workflow

143

andreaserradev-gbj/dev-workflow

Plugin Claude Code

Claude Code skills for multi-session development workflows: plan features with structured PRDs, checkpoint progress, and resume across sessions.

2 4d ago A tokens not measured original MIT