cog: Command for Claude Code

.claude/commands/reflect.md

reflect is a command for Claude Code from marciopuga/cog. It costs 47 tokens per session (2,115 once invoked), scanned A, original, MIT.

A command that reviews recent interactions and stored notes to find patterns, resolve contradictions, and improve an ongoing personal knowledge base.

In plain words
What is it for?
It is for regular review of recent changes, observations, recurring patterns, important notes, and possible future discussion threads.
Why use it?
It reduces the manual effort of keeping memory files consistent and useful over time.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is marciopuga/cog's own configuration. It tells Claude Code how to work on cog itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cog configures →

Reuse

Borrowing it

Nothing to install: this file belongs to marciopuga/cog. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/marciopuga/cog/main/.claude/commands/reflect.md
Clone the repo
git clone --depth 1 https://github.com/marciopuga/cog

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.

agentmods badge for reflect

README.md
[![agentmods](https://agentmods.dev/badge/commands/marciopuga/cog/reflect/github.svg)](https://agentmods.dev/commands/marciopuga/cog/reflect)
Your own site
<a href="https://agentmods.dev/commands/marciopuga/cog/reflect"><img src="https://agentmods.dev/badge/commands/marciopuga/cog/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.

agentmods 80×15 button for reflect

Your own site · 80×15
<a href="https://agentmods.dev/commands/marciopuga/cog/reflect"><img src="https://agentmods.dev/badge/commands/marciopuga/cog/reflect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,115 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.02115
Opus 5.5 $0.00019 $0.00846
Sonnet 5.5 $0.00009 $0.00423
Haiku 4.5 $0.00005 $0.00212

Measured 2mo ago against content hash 80e8f8b6e419, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reflect scanned grade A with 0 findings 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 2mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/reflect.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cog Reflect

Self-reflection and memory consolidation. Past-facing — reads memory, fixes contradictions, distills patterns. Reflect never sees transcripts: everything it knows comes from what was written to memory, so an interaction that was never captured is invisible here.

Take your time. This is a deep session. Read broadly, cross-reference, and ACT on findings. You're the maintainer of the knowledge base.

Memory Path

All files under the resolved memory path: $COG_HOME/memory/ if COG_HOME is set, otherwise ~/cog/memory/.

Orientation (run first)

Scope your work before reading files:

  1. Find files changed since the last run — read memory/cog-meta/run-log.md for the last /reflect entry and scope to files modified since that date (no entry → default to the last 7 days)
  2. Read memory/domains.yml, then INDEX.md only for domains that have changed files — the index gives L0 + line counts per file. Don't grep L0 headers across the whole tree. Never edit an INDEX.md — housekeeping regenerates them; a week of drift in line counts is harmless.
  3. Check observation entry counts (archival threshold = 50)

Focus on recently-changed files. Skip unchanged ones.

Minimum Data Check

Before proceeding, verify there's enough material to work with:

  • If total observations across all domains < 5: stop. Say "Not enough data yet. Keep capturing observations and run again when you have more material."
  • If no files were modified in the last 7 days: flag it. "Memory hasn't been updated recently. Consider capturing some observations first."
  • If patterns.md is empty and observations < 10: say "Too early to consolidate. You need ~10+ observations before patterns emerge."

Don't produce low-quality output from insufficient data. It's better to say "not yet" than to force weak patterns.

Files to Read

  • memory/cog-meta/self-observations.md
  • memory/cog-meta/patterns.md
  • memory/cog-meta/action-items.md (open [housekeeping] routes and pri:low ideas)
  • memory/cog-meta/scenarios/*.md (active scenarios, for the retrospective step)
  • All domain observations.md files
  • All domain action-items.md files
  • All hot-memory.md files

Read the full file on GitHub · 167 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.

  1. 2mo ago Changed · -1 lines · +4 tokens per session 80e8f8b6e419
  2. 2mo ago First seen · 168 lines · 43 tokens per session scan A 79c6de17c7ef

Subscribe to this mod's changes

reflect is a command published in the GitHub repository marciopuga/cog (377 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 2,115 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

reflect compared with commands from other repositories

reflect next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
reflectmarciopuga/cogCommand3772mo agoMITA47Claude Code
minutes-ideassilverstein/minutesCommand1.6kyesterdayMITA48Claude Code, OpenCode
learnReflexioAI/claude-smartCommand7913d agoApache-2.0A14Claude Code
memory-storeverygoodplugins/mcp-automemCommand66todayMITA10Claude Code
analyze-contextRohiRIK/OpenLtmCommand298d agoMITA39Claude Code
cc-memoryTheLobbi/claudeCommand217d agoMITA0Claude Code
lians-recallLians-ai/LiansCommand174d agoApache-2.0A19Claude Code