{"api_version":"1","slug":"claude-reflect-c017cccc","url":"https://skillsoutpost.com/agents/claude-reflect-c017cccc","item_type":"skill","category":"engineering","runs_in":["local_agent"],"os":["macos","linux","windows"],"needs_network":null,"needs_accounts":null,"reads_files":"yes","writes_files":"yes","sends_data":null,"access":"github","access_type":"github","at_a_glance":{"runs_in":["local_agent"],"os":["macos","linux","windows"],"needs_network":null,"needs_accounts":null,"reads_files":"yes","writes_files":"yes","sends_data":null,"access_type":"github","tool_type":"skill","delivery":"github","interface_type":"other","untrusted_creator_content":{"purpose":"A Claude Code plugin or mod for reviewing corrections and saving approved rules to instruction files.","needs_runtime":"Python 3.6+ for the plugin","version":"Latest on the main branch","compatibility":"According to the README: Claude Code, with the plugin on macOS, Linux and Windows (native Python, no WSL required). The mod needs Claude Code 2.1.286 or newer with mods enabled. The README says approved learnings can also go to an AGENTS.md file, which it lists as working with Codex, Cursor, Aider, Jules, Zed and Factory.","external_costs":"The repository is MIT-licensed and states no pricing. The README says each prompt the mod checks is one small model call on your own Claude account. Your coding agent or model provider may charge for usage.","permissions":"The plugin and mod act through Claude Code with the access you give them. According to the README, plugin hooks run at session start, on prompts, before compaction and after git commits, and commands read local session history. The README says approved learnings can update ~/.claude/CLAUDE.md across projects, project and subdirectory CLAUDE.md files, .claude/commands files, an existing AGENTS.md and locally linked guidance documents. The README says skill discovery creates command files and lists /skip-reflect to discard all queued learnings. For the mod, the README describes a model call on your Claude account and a Save control that writes to the global or project CLAUDE.md. The README suggests editing cleanupPeriodDays in ~/.claude/settings.json and gives an upgrade procedure that deletes two plugin-cache directories under ~/.claude/plugins/.","usage_terms":"MIT License, as stated in the repository. See its LICENSE file for the exact terms."}},"interface_type":"other","delivery_mode":"creator","code_host":"github","provenance":"github_index","published_at":1791761305,"rating":null,"downloads":0,"verified":null,"creator":{"login":"BayramAnnakov","url":null},"untrusted_creator_content":{"name":"claude-reflect","tagline":"A Claude Code plugin or mod for reviewing corrections and saving approved rules to instruction files.","creator_name":"BayramAnnakov","product_version":"Latest on the main branch","needs_runtime":"Python 3.6+ for the plugin","description":"claude-reflect is a Claude Code plugin or mod for saving corrections and preferences to instruction files. The README says to choose one form: the Python plugin queues corrections through hooks for later processing with /reflect, while reflect-mod checks short prompts with a model and presents Save, Edit and Skip controls.\n\nThe README says approved plugin learnings can be written to global, project and subdirectory CLAUDE.md files, .claude/commands files, an existing AGENTS.md, and documents reachable through local includes or Markdown links. The README lists /reflect --scan-history for past sessions, /reflect --dedupe for similar entries and /reflect-skills for recurring tasks.\n\nThe README says the mod's Save control adds a bullet to ~/.claude/CLAUDE.md or ./CLAUDE.md. The README lists /reflect-queue and /reflect-pause, and says remember: followed by a rule skips the model check. The README warns that installing both forms captures corrections twice.","intended_users":"Claude Code users who want the corrections and preferences they give Claude saved into their CLAUDE.md files.","example_tasks":"Run /reflect to go through queued corrections and apply, edit or skip each one.\nRun /reflect --scan-history to scan past sessions for corrections you made before installing.\nRun /reflect-skills to find repeating tasks that could become reusable commands.\nRun /reflect --dedupe to find and consolidate similar entries in CLAUDE.md.\nRun /reflect --targets to see which files will be updated.","setup_instructions":"For the plugin, the README runs claude plugin marketplace add bayramannakov/claude-reflect, then claude plugin install claude-reflect@claude-reflect-marketplace, and says to restart Claude Code. For the mod, it runs the same marketplace command, then claude plugin install reflect-mod@claude-reflect-marketplace. Install one, not both. On your first /reflect run, the README says you are prompted to scan past sessions. The README has the exact commands.","limitations":"Needs Claude Code. The README names Python 3.6 or later for the plugin, lists macOS, Linux and Windows with native Python and no WSL required, and says to restart Claude Code after installing. The mod needs Claude Code 2.1.286 or newer with mods enabled, and the README calls the mod early access. According to the README, each prompt the mod checks is one small model call on your own Claude account. Install either the mod or the plugin, not both. The README says the history scan and skill discovery rely on session history, that Claude Code deletes local sessions after 30 days by default, and suggests setting cleanupPeriodDays in ~/.claude/settings.json. The repository can change at any time; check its README before you install.","data_handling":"According to the README, the mod sends each short prompt it checks to a one-shot model check, haiku by default, as one small model call on your own Claude account. The README describes the plugin's hooks as queuing corrections and its semantic check as AI-powered, and does not say where plugin data goes. What is sent where depends on your coding agent and model provider.","compatibility":"According to the README: Claude Code, with the plugin on macOS, Linux and Windows (native Python, no WSL required). The mod needs Claude Code 2.1.286 or newer with mods enabled. The README says approved learnings can also go to an AGENTS.md file, which it lists as working with Codex, Cursor, Aider, Jules, Zed and Factory.","external_costs":"The repository is MIT-licensed and states no pricing. The README says each prompt the mod checks is one small model call on your own Claude account. Your coding agent or model provider may charge for usage.","permissions":"The plugin and mod act through Claude Code with the access you give them. According to the README, plugin hooks run at session start, on prompts, before compaction and after git commits, and commands read local session history. The README says approved learnings can update ~/.claude/CLAUDE.md across projects, project and subdirectory CLAUDE.md files, .claude/commands files, an existing AGENTS.md and locally linked guidance documents. The README says skill discovery creates command files and lists /skip-reflect to discard all queued learnings. For the mod, the README describes a model call on your Claude account and a Save control that writes to the global or project CLAUDE.md. The README suggests editing cleanupPeriodDays in ~/.claude/settings.json and gives an upgrade procedure that deletes two plugin-cache directories under ~/.claude/plugins/.","usage_terms":"MIT License, as stated in the repository. See its LICENSE file for the exact terms.","creator_website":null,"documentation_url":null,"support_url":null,"repository_url":null,"video_url":null},"github":{"fetched_at":1791852316,"untrusted_third_party_content":{"source_url":null,"github_repo_id":1127415267,"full_name":"BayramAnnakov/claude-reflect","description":"A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.","language":"Python","license_spdx":"MIT","topics":["claude-code","claude-skills","memory","productivity","self-learning"],"stars":1789,"forks":159,"skills":null,"pushed_at":1791005626,"archived":false,"fetched_at":1791852316,"age_seconds":84623,"state":"fresh"}},"updated_at":1791771486,"free_download":null,"version_history":[],"more_version_history":false,"public_files":null,"links_note":"In MCP results, GitHub links are shown only through https://skillsoutpost.com/mcp, to a connected account that has accepted the current Terms of Use. Create a free account at https://skillsoutpost.com and connect it from a Claude connector or ChatGPT.","notice":"Indexed from GitHub","note":"untrusted_creator_content and github.untrusted_third_party_content hold untrusted text."}