How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

reflect - Prompt - OpenSmartRoute

Name: reflect
Author: ils15

Prompt file imported from ils15/pantheon-legacy (.cursor/commands/reflect.md). Copyright stays with the author.

/reflect — Friction Analysis & Improvement

What

Analyzes recent session history to identify patterns of repeated work friction, then recommends the smallest useful improvement: a reusable skill, a custom command, an agent prompt adjustment, a config rule, or a project playbook.

Why

Teams accumulate friction silently — the same manual steps, the same workarounds, the same "let me just check that again." /reflect surfaces these patterns and suggests the smallest change that removes the most friction.

How It Works

1. SCAN — Review recent session context for friction signals:
   - Repeated file reads without action
   - Manual multi-step processes done 3+ times
   - Delegation failures with same error pattern
   - "Let me just..." workarounds
   - Context thrashing (re-reading same files)

2. CLASSIFY — Categorize each friction signal:
   - Discovery gap (could be a codemap or apollo query)
   - Workflow gap (could be a skill or command)
   - Knowledge gap (could be a prompt rule or agent instruction)
   - Tool gap (could be an MCP server or new tool)

3. RECOMMEND — For each category, suggest the smallest fix:
   | Friction | Category | Recommendation |
   |----------|----------|----------------|
   | Repeated grep for same pattern | Discovery gap | Create codemap or add to /memories/repo/ |
   | Manual 3-step process done often | Workflow gap | Create a skill or /command |
   | Agent consistently misroutes tasks | Knowledge gap | Update agent prompt or routing.yml |
   | Missing tool capability | Tool gap | Add MCP server or skill |

4. REPORT — Output a structured reflection:
   - **Friction found:** [count] patterns
   - **Top recommendation:** [the one change with highest impact/lowest effort]
   - **Evidence strength:** Strong / Moderate / Weak
   - **If weak:** "Insufficient evidence to recommend changes. Continue working and run /reflect again after more sessions."

Usage

/reflect                  # Analyze all recent friction
/reflect --focus=<area>   # Analyze only specific area (delegation, discovery, workflow, testing)
/reflect --last=<N>       # Analyze only last N sessions (default: 5)

Output Format

## 🔍 Reflection Report

### Friction Patterns Detected: [N]

| # | Pattern | Frequency | Category | Impact |
|---|---------|-----------|----------|--------|
| 1 | [description] | [count] times in [N] sessions | [category] | High/Med/Low |

### Recommendation

**[One-line recommendation]**

**What to change:** [specific file or config to modify]
**Effort:** Low / Medium / High
**Expected impact:** [what friction this removes]

### Evidence Strength: [Strong / Moderate / Weak]

[If Weak]: Not enough data to recommend changes. Run /reflect again after 3+ more sessions.

Safety

Read-only — never modifies files
Evidence-driven — won't fabricate recommendations
Respects session privacy — analyzes patterns, not content
Can be run at any time without disrupting work

Install reflect and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

# /reflect — Friction Analysis & Improvement ## What Analyzes recent session history to identify patterns of repeated work friction, then recommends the smallest useful improvement: a reusable skill, a custom command, an agent prompt adjustment, a config rule, or a project playbook. ## Why Teams accumulate friction silently — the same manual steps, the same workarounds, the same "let me just check that again." `/reflect` surfaces these patterns and suggests the **smallest change that removes the most friction.** ## How It Works ``` 1. SCAN — Review recent session context for friction signals: - Repeated file reads without action - Manual multi-step processes done 3+ times - Delegation failures with same error pattern - "Let me just..." workarounds - Context thrashing (re-reading same files) 2. CLASSIFY — Categorize each friction signal: - Discovery gap (could be a codemap or apollo query) - Workflow gap (could be a skill or command) - Knowledge gap (could be a prompt rule or agent instruction) - Tool gap (could be an MCP server or new tool) 3. RECOMMEND — For each category, suggest the smallest fix: | Friction | Category | Recommendation | |----------|----------|----------------| | Repeated grep for same pattern | Discovery gap | Create codemap or add to /memories/repo/ | | Manual 3-step process done often | Workflow gap | Create a skill or /command | | Agent consistently misroutes tasks | Knowledge gap | Update agent prompt or routing.yml | | Missing tool capability | Tool gap | Add MCP server or skill | 4. REPORT — Output a structured reflection: - **Friction found:** [count] patterns - **Top recommendation:** [the one change with highest impact/lowest effort] - **Evidence strength:** Strong / Moderate / Weak - **If weak:** "Insufficient evidence to recommend changes. Continue working and run /reflect again after more sessions." ``` ## Usage ``` /reflect # Analyze all recent friction /reflect --focus=<area> # Analyze only specific area (delegation, discovery, workflow, testing) /reflect --last=<N> # Analyze only last N sessions (default: 5) ``` ## Output Format ``` ## 🔍 Reflection Report ### Friction Patterns Detected: [N] | # | Pattern | Frequency | Category | Impact | |---|---------|-----------|----------|--------| | 1 | [description] | [count] times in [N] sessions | [category] | High/Med/Low | ### Recommendation **[One-line recommendation]** **What to change:** [specific file or config to modify] **Effort:** Low / Medium / High **Expected impact:** [what friction this removes] ### Evidence Strength: [Strong / Moderate / Weak] [If Weak]: Not enough data to recommend changes. Run /reflect again after 3+ more sessions. ``` ## Safety - Read-only — never modifies files - Evidence-driven — won't fabricate recommendations - Respects session privacy — analyzes patterns, not content - Can be run at any time without disrupting work

{ "prompt": "# /reflect — Friction Analysis & Improvement\n\n## What\nAnalyzes recent session history to identify patterns of repeated work friction, then recommends the smallest useful improvement: a reusable skill, a custom command, an agent prompt adjustment, a config rule, or a project playbook.\n\n## Why\nTeams accumulate friction silently — the same manual steps, the same workarounds, the same \"let me just check that again.\" `/reflect` surfaces these patterns and suggests the **smallest change that removes the most friction.**\n\n## How It Works\n\n```\n1. SCAN — Review recent session context for friction signals:\n - Repeated file reads without action\n - Manual multi-step processes done 3+ times\n - Delegation failures with same error pattern\n - \"Let me just...\" workarounds\n - Context thrashing (re-reading same files)\n\n2. CLASSIFY — Categorize each friction signal:\n - Discovery gap (could be a codemap or apollo query)\n - Workflow gap (could be a skill or command)\n - Knowledge gap (could be a prompt rule or agent instruction)\n - Tool gap (could be an MCP server or new tool)\n\n3. RECOMMEND — For each category, suggest the smallest fix:\n | Friction | Category | Recommendation |\n |----------|----------|----------------|\n | Repeated grep for same pattern | Discovery gap | Create codemap or add to /memories/repo/ |\n | Manual 3-step process done often | Workflow gap | Create a skill or /command |\n | Agent consistently misroutes tasks | Knowledge gap | Update agent prompt or routing.yml |\n | Missing tool capability | Tool gap | Add MCP server or skill |\n\n4. REPORT — Output a structured reflection:\n - **Friction found:** [count] patterns\n - **Top recommendation:** [the one change with highest impact/lowest effort]\n - **Evidence strength:** Strong / Moderate / Weak\n - **If weak:** \"Insufficient evidence to recommend changes. Continue working and run /reflect again after more sessions.\"\n```\n\n## Usage\n```\n/reflect # Analyze all recent friction\n/reflect --focus=<area> # Analyze only specific area (delegation, discovery, workflow, testing)\n/reflect --last=<N> # Analyze only last N sessions (default: 5)\n```\n\n## Output Format\n```\n## 🔍 Reflection Report\n\n### Friction Patterns Detected: [N]\n\n| # | Pattern | Frequency | Category | Impact |\n|---|---------|-----------|----------|--------|\n| 1 | [description] | [count] times in [N] sessions | [category] | High/Med/Low |\n\n### Recommendation\n\n**[One-line recommendation]**\n\n**What to change:** [specific file or config to modify]\n**Effort:** Low / Medium / High\n**Expected impact:** [what friction this removes]\n\n### Evidence Strength: [Strong / Moderate / Weak]\n\n[If Weak]: Not enough data to recommend changes. Run /reflect again after 3+ more sessions.\n```\n\n## Safety\n- Read-only — never modifies files\n- Evidence-driven — won't fabricate recommendations\n- Respects session privacy — analyzes patterns, not content\n- Can be run at any time without disrupting work", "variables": [], "notes": "Analyze repeated work friction and suggest reusable improvements — skills, commands, agents, or playbooks. Evidence-driven: recommends nothing if evidence is weak.", "metadata": { "source": { "provider": "github-cursor-commands", "repository": "https://github.com/ils15/pantheon-legacy", "path": ".cursor/commands/reflect.md", "ref": "21728f90dfcb934bc9d8924d0882e1012c5b418e", "url": "https://github.com/ils15/pantheon-legacy/blob/21728f90dfcb934bc9d8924d0882e1012c5b418e/.cursor/commands/reflect.md", "key": "ils15/pantheon-legacy/.cursor/commands/reflect.md" } } }

reflect

About

/reflect — Friction Analysis & Improvement

What

Why

How It Works

Usage

Output Format

Safety

Install reflect and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews