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…
Plugin bundle · by chanjoongx
About
reflect is a plugin bundle for AI coding tools published by chanjoongx. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). We first saw it on 2026-10-11 and have recorded no change since. As of our marketplace pass on 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
What it asks for
- Installs as a plugin bundle
- Hooks: 2
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Works with
- Claude Code
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a Claude Code plugin
Built from what Claude Code: claude-plugins-community declares.
/plugin marketplace add anthropics/claude-plugins-community
/plugin install reflect@claude-communityWhere it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Open the source on GitHub) | Listed | 0.1.4 | Forks (GitHub): 0 Stars (GitHub): 0 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
What the bundle contains
As published on Claude Code: claude-plugins-community.
Commands: 1
brain-reflect
Agents: 1
reflection-orchestrator
Hooks: 2
PostToolUseUserPromptSubmit
What changed
Nothing has moved on this plugin since we started watching it.
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
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…
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on 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…
Has a listing on 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…
Has a listing on 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.
Has a listing on 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.
Has a listing on 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…
Has a listing on 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.
Has a listing on 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…
Has a listing on 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.
Has a listing on 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).
Has a listing on 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.
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Is this your plugin?
Add it to your projects and prove you maintain it with a file in its repository, a file on your domain or a DNS record. You get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.