Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ccplugins/awesome-claude-code-plugins/plugin install claude-reflectWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ccplugins/awesome-claude-code-plugins/reflect)<a href="https://agentmods.dev/commands/ccplugins/awesome-claude-code-plugins/reflect"><img src="https://agentmods.dev/badge/commands/ccplugins/awesome-claude-code-plugins/reflect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ccplugins/awesome-claude-code-plugins/reflect"><img src="https://agentmods.dev/badge/commands/ccplugins/awesome-claude-code-plugins/reflect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.07358 |
| Opus 5.5 | $0.00006 | $0.02943 |
| Sonnet 5.5 | $0.00003 | $0.01472 |
| Haiku 4.5 | $0.00002 | $0.00736 |
Grade B, and why
reflect scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Learnings queue: !`cat ~/.claude/learnings-queue.json 2>/dev/null || echo "[]"` How it starts
The opening of the file, as written. The whole thing — 809 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
--dry-run: Preview all changes without prompting or writing.--scan-history: Scan ALL past sessions for corrections (useful for first-time setup or cold start).--days N: Limit history scan to last N days (default: 30). Only used with--scan-history.--targets: Show detected AI assistant config files and exit.--review: Show learnings with stale/decayed entries for review.--dedupe: Scan CLAUDE.md for similar entries and propose consolidations.
Context
- Project CLAUDE.md: @CLAUDE.md
- Global CLAUDE.md: @~/.claude/CLAUDE.md
- Learnings queue: !
cat ~/.claude/learnings-queue.json 2>/dev/null || echo "[]" - Current project: !
pwd
Multi-Target Export
Claude-reflect syncs learnings to CLAUDE.md and AGENTS.md (the emerging cross-tool standard).
Supported Targets:
| Target | File Path | Format | Notes |
|---|---|---|---|
| Claude Code | ~/.claude/CLAUDE.md, ./CLAUDE.md |
Markdown | Always enabled |
| AGENTS.md | ./AGENTS.md |
Markdown | Industry standard (Codex, Cursor, Aider, Jules, Zed, Factory) |
Detection Logic:
# Always enabled
~/.claude/CLAUDE.md
./CLAUDE.md (if exists)
# Only if file exists
test -f AGENTS.md && echo "AGENTS.md"
Note on Confidence & Decay:
- Confidence scores help prioritize learnings during
/reflectreview - Decay applies to queue items only — if a learning sits unprocessed for too long, it's flagged as stale
- Once applied to CLAUDE.md, entries are permanent (edit manually to remove)
Your Task
Handle --targets Argument
If user passed --targets:
Detect and display all AI assistant config files in the current project:
echo "=== Detected AI Assistant Configs ==="
echo ""
echo "✓ ~/.claude/CLAUDE.md (Claude Code - always enabled)"
test -f CLAUDE.md && echo "✓ ./CLAUDE.md (Project)" || echo "✗ ./CLAUDE.md (not found)"
test -f AGENTS.md && echo "✓ AGENTS.md (Codex, Cursor, Aider, Jules, Zed)" || echo "✗ AGENTS.md (not found)"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 809 lines · 15 tokens per session scan B 3b38439aa611
reflect is a command published in the GitHub repository ccplugins/awesome-claude-code-plugins (977 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 7,358 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
create-pull-request
Provides comprehensive PR creation guidance with GitHub CLI, enforcing title conventions, following template structure, and offering concrete command examples with best practices.
pr-issue-resolve
Follow these steps to analyze suggested changes (e.g., review comments, inline suggestions, or requested modifications) in a GitHub Pull Request (PR) and resolve them efficiently. The goal is to review, understand, plan fixes, apply changes, test, and update the PR while maintaining code quality and collaboration.
openapi-expert
Use this agent when you need to update, synchronize, or validate the OpenAPI specification (openapi.yml) against the actual REST API implementation. This includes adding new endpoints, updating request/response schemas, fixing discrepancies between the spec and code, or ensuring complete API documentation coverage.
husky
Sets up and manages Husky Git hooks by configuring pre-commit hooks, establishing commit message standards, integrating with linting tools, and ensuring code quality on commits.
pr-review
Reviews pull request changes to provide feedback, check for issues, and suggest improvements before merging into the main codebase.
create-pr
Streamlines pull request creation by handling the entire workflow: creating a new branch, committing changes, formatting modified files with Biome, and submitting the PR.