Borrowing it
Nothing to install: this file belongs to Everyone-Needs-A-Copilot/claude-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Everyone-Needs-A-Copilot/claude-copilot/main/.claude/commands/reflect.mdgit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote 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/everyone-needs-a-copilot/claude-copilot/reflect)<a href="https://agentmods.dev/commands/everyone-needs-a-copilot/claude-copilot/reflect"><img src="https://agentmods.dev/badge/commands/everyone-needs-a-copilot/claude-copilot/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/everyone-needs-a-copilot/claude-copilot/reflect"><img src="https://agentmods.dev/badge/commands/everyone-needs-a-copilot/claude-copilot/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 | $0.00000 | $0.01049 |
| Opus 5.5 | $0.00000 | $0.00420 |
| Sonnet 5.5 | $0.00000 | $0.00210 |
| Haiku 4.5 | $0.00000 | $0.00105 |
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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflect Command
Review session memory for reasoning gaps/errors and store confirmed corrections.
Read and apply .claude/agents/_shared/work-lifecycle.md once per task.
Overview
End-of-session review uses cc memory, replacing removed MCP correction_*
tools. No automatic correction-pattern detection, pending/approved/rejected queue,
or skill/agent routing remains. Update SKILL.md/agent files directly or delegate
to @agent-me when a correction warrants it.
Arguments
- No arguments: review recent
lesson,decision, andcontextentries. --type <lesson|decision|context|reference>: review only one entry type.<search terms>: review entries matching a topic (usescc memory search).
Step 1: Gather Memory
# Default review: recent lessons, decisions, and context (project scope)
cc memory list --type lesson --json
cc memory list --type decision --json
cc memory list --type context --json
# Single type (when --type is passed)
cc memory list --type <type> --json
# Topic review (when search terms are passed)
cc memory search "<terms>" --json
Read fuller content for any entry by UUID (full or prefix match):
cc memory get <entry-id>
Step 2: Present a Review Dashboard
Group entries by type, newest first, with IDs and ~100-character excerpts:
## Session Reflection
**Stored this session:** <counts by type>
### <Type>
- [<id>] "<excerpt>"
Step 3: Reflect
Review the session against what was stored and surface:
- Gaps — decisions made but not recorded as
decisionentries. - Errors — guidance given that later proved wrong (candidate
lessonentries). - Stale entries — memory that is now outdated or contradicted.
Reconcile these in the existing canonical record, retaining prior authority and contrary evidence. Add a memory locator only if retrieval needs it; obtain exact approval for destructive removal.
Step 4: Store Corrections
Update the canonical record first; store only useful memory pointers with source and applicability boundary:
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.
- 7d ago Changed · +2 lines b4aba6c7cc68
- 1mo ago Changed · -32 lines adcc6b49a350
- 1mo ago Changed · +20 lines 50c2c1f1c8b7
- 1mo ago First seen · 138 lines · 0 tokens per session scan A 91729ddc31a3
reflect is a command published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (14 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,049 tokens. 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 2026-09-04.
Other commands, from other repositories
instinct-import
Import instincts from external sources.
learn
Extract patterns and learnings from current session.
context-save
Save project context, decisions, and progress for a later session.
export-closedloop-learnings
Exports pending ClosedLoop learnings to global location with deduplication.
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
cleanup
Sweep /.claude disk hygiene to stated retentions, clean up stale plans from repos, audit plugin health, and compact agent memory files.