reflect
Session-local metacognition harness for long-running Claude Code work. When suggestions get reverted 3+ times within 10 tool calls, reflect invokes Opus 4.7 to reason about why…
Paquete de plugins · de chanjoongx
Resumen
reflect es un paquete de plugins para herramientas de programación con IA publicado por chanjoongx. Marketplaces que leemos y que lo publican: 1 (Claude Code: claude-plugins-community). Lo vimos por primera vez el 2026-10-11 y desde entonces no hemos registrado cambios. Según nuestra pasada por los marketplaces del 2026-10-13.
Session-local metacognition harness for long-running Claude Code work. When suggestions get reverted 3+ times within 10 tool calls, reflect invokes Opus 4.7 to reason about why the rejections clustered. The model reads back the last 20 tool calls, the rolled-back diff, and active rules, then writes structured guidance — pattern, signal, adjustment, confidence — to .reflect/session-guidance.md. The next turn auto-loads it via path-scoped rule injection and adjusts. Key features: • 3-tier weighted signal taxonomy: git revert/restore (Tier 1, +100), user-file deletes (Tier 2, +70), utterance negation regex (Tier 3, +50). Cumulative threshold 240 + 5-turn cooldown — fires only when reverts genuinely cluster. • Single-shot Opus 4.7 with adaptive thinking (effort: high) and 3-layer prompt cache (L1 1h, L2 5m, L3 ephemeral). Measured: cold ~$0.05, warm ~$0.01, 95.9% L1 cache hit. • Two cross-platform hooks: PostToolUse (Tier 1+2) and UserPromptSubmit (Tier 3). Pure-bash arithmetic — no jq/bc dependency on Windows gi
Qué pide
- Se instala como paquete de plugins
- Hooks declarados: 2
Lo que declara, pide y ejecuta, completo
Instale solo plugins de desarrolladores en los que confíe. Mostramos lo que publican los marketplaces y no probamos plugins.
Funciona con
- Claude Code
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por usted ni probamos plugins.
Como plugin de Claude Code
Generado a partir de lo que declara Claude Code: claude-plugins-community.
/plugin marketplace add anthropics/claude-plugins-community
/plugin install reflect@claude-communityDónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Abrir el código en GitHub) | Publicado | 0.1.4 | Forks (GitHub): 0 Estrellas (GitHub): 0 |
Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
Qué contiene el paquete
Tal como se publica en Claude Code: claude-plugins-community.
Comandos: 1
brain-reflect
Agentes: 1
reflection-orchestrator
Hooks: 2
PostToolUseUserPromptSubmit
Qué cambió
Nada ha cambiado en este plugin desde que lo seguimos.
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta lista.
-
Every Claude Code edit becomes a Causari event with its prompt, model and diff; ask `why` for any line. Needs the `re` binary from causari.dev.
-
claude-human-review adds a human approval gate at the end of every Claude Code turn that edits files. When Claude tries to stop, the plugin pauses it and has Claude do two things…
-
Say it once. jevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, brings the relevant ones back next session, and checks…
-
Self-improving measurement layer for Claude Code. Reads JSONL session data, computes effectiveness metrics, writes behavioral rules into CLAUDE.md.
-
PDCA memory loop for Claude Code — prevents "AI fixed bug X and broke feature Y" across iterations. Installs a three-tier memory system in your project (project-memory…
-
Claude Code user plugin for filing well-formed bug reports, feature requests, model-behavior reports, and docs issues against anthropics/claude-code
-
Self-improving memory for Claude Code. Observes hooks (tool use, edits, errors, guard blocks), distills recurring patterns into durable rules, and surfaces relevant approved…
-
Save and restore named session checkpoints so you can pick up exactly where you left off across Claude Code sessions.
-
Persistent cross-session memory for Claude Code. Neutrally auto-injects your project context, decisions, and tech stack at session start so Claude already knows who you are and…
-
A SME of SWE: a plugin giving Claude Code the expertise of an Expert Software Engineer across every SWE area, while still inviting novice programmers to make gains on…
Plugins similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en Claude Code: claude-plugins-community (5)
-
claude-human-review adds a human approval gate at the end of every Claude Code turn that edits files. When Claude tries to stop, the plugin pauses it and has Claude do two things…
-
Self-improving measurement layer for Claude Code. Reads JSONL session data, computes effectiveness metrics, writes behavioral rules into CLAUDE.md.
-
PDCA memory loop for Claude Code — prevents "AI fixed bug X and broke feature Y" across iterations. Installs a three-tier memory system in your project (project-memory…
-
Claude Code user plugin for filing well-formed bug reports, feature requests, model-behavior reports, and docs issues against anthropics/claude-code
-
Self-improving memory for Claude Code. Observes hooks (tool use, edits, errors, guard blocks), distills recurring patterns into durable rules, and surfaces relevant approved…
Publicado en Claude Code: claude-plugins-official (5)
-
Interactive self-referential AI loops for iterative development, implementing the Ralph Wiggum technique. Claude works on the same task repeatedly, seeing its previous work, until…
-
Agent that simplifies and refines code for clarity, consistency, and maintainability while preserving functionality. Focuses on recently modified code.
-
Langfuse observability plugin for Claude Code — captures and exports traces, spans, and session telemetry from Claude Code to Langfuse for LLM monitoring, debugging, and evaluation
-
Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects…
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
Publicado en Claude: knowledge-work-plugins (5)
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Streamline engineering workflows — standups, code review, architecture decisions, incident response, and technical documentation. Works with your existing tools or standalone.
Publicado en Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
AI-powered code review in Codex, powered by CodeRabbit.
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
Qodo setup, code intelligence, and review workflows.
Publicado en Community GitHub marketplaces (5)
-
Every Claude Code edit becomes a Causari event with its prompt, model and diff; ask `why` for any line. Needs the `re` binary from causari.dev.
-
Say it once. jevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, brings the relevant ones back next session, and checks…
-
memharness io.github.las7/memharness
Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.
-
Community of Consciousness MCP Server — upload and explore collective wisdom via GitHub.
-
vardoger personalizes Claude Code by analyzing your own conversation history and turning recurring patterns into tailored rules. How it works: the plugin's `analyze` skill calls…
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Preserves or recovers the reasoning behind a codebase — architectural decisions, rejected alternatives, workarounds, incident learnings, operational constraints, and historical…
-
Turn the code edits Copilot made in your session into an interactive lesson: a step-by-step walkthrough of each change with before/after views and quizzes, then a hands-on…
-
Goal-driven task orchestration with independent verification. Interviews the user to define a clear goal, then loops between a Builder subagent (does the work) and an Inspector…
-
Tools and techniques for maximizing GitHub Copilot effectiveness through better context management. Includes guidelines for structuring code, an agent for planning multi-file…
-
Shows live prompt-cache reuse, expiry, token composition, and AIU cost for the current GitHub Copilot session without making model calls.
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Advanced Security plugin for GitHub Copilot.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Navigate and interact with your C++ code using the Microsoft C++ Language Server.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
Publicado en Cursor: cursor/plugins (5)
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
Publicado en Docker MCP Catalog (5)
-
Sequential Thinking (Reference)
Dynamic and reflective problem-solving through thought sequences.
-
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
MCP server for terminal commands, file operations, and process management
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
Publicado en Official MCP Registry (5)
-
memharness io.github.las7/memharness
Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.
-
Community of Consciousness MCP Server — upload and explore collective wisdom via GitHub.
-
Context Assurance for AI agents: context engineering, AI cost optimization, verification.
-
Software design skills for AI coding agents, inspired by A Philosophy of Software Design.
-
Pre-commit code quality guardian. Detects semantic drift in AI-generated code.
Encontrados por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Es tu plugin?
Añádelo a tus proyectos y demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS. Recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Datos de Claude Code: claude-plugins-community. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.