reprompt

ctxray wrappedgenerates a Spotify Wrapped-style report of your AI interactions — your persona (Debugger? Architect? Explorer?), top patterns, and a shareable card.

ctxray insightscompares your actual prompting habits against research-backed benchmarks. Are your prompts specific enough? Do you front-load instructions? How much context do you provide?

ctxray privacy --deepscans every prompt you've sent for API keys, tokens, passwords, and PII. See exactly what you've shared with which AI tool.

ctxray check "your prompt"scores, lints, and rewrites in one command — no LLM, <50ms.

ctxray check "fix the auth bug in login.ts" # threshold pass/fail + diagnostics ctxray check "fix bug" --model claude # model-specific scoring for Claude ctxray check "refactor middleware" --threshold 50 # custom threshold for stricter teams

ctxray rewrite— rule-based prompt improvement

ctxray build— assemble prompts from components

Captured prompts sync locally via Native Messaging — nothing leaves your machine.

# .github/workflows/prompt-lint.yml name: Prompt Quality on: pull_request jobs: lint: runs-on: ubuntu-latest permissions: pull-requests: write steps: - uses: actions/checkout@v4 - uses: ctxray/ctxray@main with: score-threshold: 43 # experimentally validated (below = 83% failure rate) model: claude # optional: model-specific rules strict: true comment-on-pr: true

# .pre-commit-config.yaml repos: - repo: https://github.com/ctxray/ctxray rev: v3.0.0 hooks: - id: ctxray-lint-score # quality threshold gate (score >= 43) # - id: ctxray-lint-claude # Claude-specific rules + threshold # - id: ctxray-lint-gpt # GPT-specific rules + threshold

ctxray lint --score-threshold 43 # exit 1 below experimentally validated threshold ctxray lint --score-threshold 50 # or set your own bar ctxray lint --model claude # model-specific lint rules ctxray lint --strict # exit 1 on warnings ctxray lint --json # machine-readable output

ctxray init # generates .ctxray.toml with all rules documented

Model-specific scoring (--model claude/gpt/gemini) applies research-backed adjustments for each model's known preferences and sensitivities.

All analysis runs locally in <1ms per prompt. No LLM calls, no network requests.

Data sources: ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │Claude Code│ │ Cursor │ │ Aider │ │ ChatGPT │ │ 5 more.. │ └─────┬────┘ └─────┬────┘ └─────┬────┘ └─────┬────┘ └─────┬────┘ └─────────────┴───────────┴─────────────┴─────────────┘ │ scan -> dedup -> store -> analyze │ ┌──────────────────┼──────────────────┐ v v v ┌──────────┐ ┌──────────────┐ ┌──────────┐ │ insights │ │ patterns │ │ sessions │ │ wrapped │ │ repetition │ │ projects │ │ style │ │ privacy │ │ agent │ └──────────┘ └──────────────┘ └──────────┘

- Pure rules, no LLM— scoring and rewriting use regex + TF-IDF + research heuristics. Deterministic, private, <1ms per prompt.
- Adapter pattern— each AI tool gets a parser that normalizes to a commonPromptmodel. Adding a new tool = one file.
- Two-layer dedup— SHA-256 for exact matches, TF-IDF cosine similarity for near-dupes.
- Research-calibrated— 10 peer-reviewed papers inform the scoring weights.

ctxray distillscores every turn in a conversation using 6 signals:

- Position— first/last turns carry framing and conclusions
- Length— substantial turns contain more information
- Tool trigger— turns that cause tool calls are action-driving
- Error recovery— turns that follow errors show problem-solving
- Semantic shift— topic changes mark conversation boundaries
- Uniqueness— novel phrasing vs repetitive follow-ups

Session type (debugging, feature-dev, exploration, refactoring) is auto-detected and signal weights adapt accordingly.

- 100% local— your prompts never leave your machine
- No LLM required— pure rule-based analysis, <50ms per prompt
- 9 AI tools— the only tool that works across Claude Code, Cursor, ChatGPT, and more
- Research-backed— calibrated against 10 peer-reviewed papers, not vibes

Previously published asreprompt-cli. Same tool, new name, clean namespace.

- All analysis runs locally. No prompts leave your machine.
- ctxray privacyshows exactly what you've sent to which AI tool.
- Optional telemetry sends only anonymous feature vectors — never prompt text.
- Open source: audit exactly what's collected.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

AI health, token usage, LLM cost optimization, BYOK vault, and cleanup audits for MCP agents.

MCP server that lets AI agents analyze Claude Code session cost & context attribution — token usage, cached re-reads, and cache writes. Local, read-only.

Behavioral trust layer for the AI agent economy. Check MCP server reliability scores, report interactions, detect anomalies, and discover the most trusted servers. 8 tools, free, real-time.

Behavioral trust scoring for MCP servers and AI agents. Live registry tracking 4,500+ servers with trust scores based on interaction history, success rates, and latency.

Integrates with PostHog for feature flag management and error tracking.

Skene is a codebase analysis toolkit for product-led growth. It scan your codebase, detect growth opportunities, and generate actionable implementation plans.

Remote MCP server (Streamable HTTP) at https://mcp.agenticrail.nz/ — deterministic step-order enforcement for AI agents. evaluate_step returns ALLOW or DENY before a step runs; verify_receipt proves a sequence's Ed25519-signed, hash-chained receipt chain is intact. No auth required: omit the bearer token and calls run on the public demo key. That first clause matters — the form has no "remote/hosted" field, and putting the endpoint in the description is the convention on that list ("Fully REMOTE! Just use…"). The rest mirrors your own server card verbatim, so the listing and the card can't drift.

Paid remote MCP for AI agent run monitoring, failure detection, tool-call incident replay, SLA receipts, and client status exports.

Deterministic security preflight for AI agents. Check URLs, files and shell commands before acting.