A workflow review command that examines a coding session for errors, repeated failed attempts, and ways to improve agent setup.

Use it to inspect a session transcript and suggest changes to agents, skills, and hooks in full, quick, or cross-session pattern modes.

It helps identify process problems that are easy to miss while working, such as repeated tool failures or unclear corrections.

reflect — Command for Claude Code by tattooinmtl

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/tattooinmtl/BlenderMCP_Dominator

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/tattooinmtl/blendermcp_dominator/reflect/github.svg)](https://agentmods.dev/commands/tattooinmtl/blendermcp_dominator/reflect)

Your own site

<a href="https://agentmods.dev/commands/tattooinmtl/blendermcp_dominator/reflect"><img src="https://agentmods.dev/badge/commands/tattooinmtl/blendermcp_dominator/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/tattooinmtl/blendermcp_dominator/reflect"><img src="https://agentmods.dev/badge/commands/tattooinmtl/blendermcp_dominator/reflect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,129 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01129
Opus 5	$0.00008	$0.00564
Sonnet 5	$0.00003	$0.00226
Haiku 4.5	$0.00002	$0.00113

Measured 8d ago against content hash b793837266b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 8d 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.

cat .claude/reflections/.patterns.json 2>/dev/null || echo "{}"

addon/blender_mcp_addon/dominator/.claude/commands/reflect.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reflect Workflow

Analyze the current session to identify workflow improvements.

Mode

$ARGUMENTS

full or empty: Full analysis with Gemini
quick: Local analysis only (faster)
patterns: Cross-session pattern analysis

Step 1: Find Transcript

# Get project hash for this directory
PROJECT_HASH=$(echo -n "$(pwd)" | md5sum | cut -d' ' -f1)
TRANSCRIPT_DIR=~/.claude/projects/$PROJECT_HASH

# Find most recent transcript
TRANSCRIPT=$(ls -t $TRANSCRIPT_DIR/*.jsonl 2>/dev/null | head -1)
echo "Transcript: $TRANSCRIPT"

If no transcript found, inform user and exit.

Step 2: Parse Session Data

Read the transcript and extract:

Tool calls (name, input, success/failure)
User messages (for corrections/friction)
Errors and retries

# Count tool calls and errors
cat "$TRANSCRIPT" | grep -c '"type":"tool_use"' || echo 0
cat "$TRANSCRIPT" | grep -c '"is_error":true' || echo 0

Step 3: Analyze Issues

Tool Failures

Look for "is_error": true in tool results
Note which tools failed and why
Check for permission, path, or syntax errors

Retry Patterns

Detect same tool called 3+ times consecutively
Indicates approach not working

User Corrections

Scan user messages for friction signals:

"no, I meant..."
"actually..."
"wait", "stop"
Redirections or corrections

Efficiency Issues

Same file read 3+ times
Same search pattern used repeatedly
Long gaps between actions

Step 4: Generate Analysis

Quick Mode

Summarize findings locally without external calls.

Full Mode

Use Gemini for deeper analysis:

gemini "Analyze this Claude Code session transcript for improvements.

Transcript path: $TRANSCRIPT

Look for:
1. Tool failures and their causes
2. Workflow friction (user corrections, abandoned approaches)
3. Missing capabilities that required workarounds
4. Efficiency issues (repeated operations, unnecessary steps)

For each issue found, suggest:
- A specific improvement (skill, hook, or agent enhancement)
- Priority (HIGH/MEDIUM/LOW)
- How to implement it

Output in this format:
ISSUE: <description>
CATEGORY: Tool Failure | Friction | Missing Capability | Efficiency
PRIORITY: HIGH | MEDIUM | LOW
EVIDENCE: <relevant excerpt>
SUGGESTION: <specific improvement>
IMPLEMENTATION: <how to add the improvement>"

Read the full file on GitHub · 196 lines

Changes

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.

8d ago First seen · 196 lines · 15 tokens per session scan B b793837266b7

Subscribe to this mod's changes

reflect is a command published in the GitHub repository tattooinmtl/BlenderMCP_Dominator (0 stars, last pushed 13d ago), licensed MIT. It adds 15 tokens to every session and 1,129 once invoked, about $0.0001 per session on Opus 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 2026-08-31.

Building agents

reflect