What is claude-self-reflect CLAUDE.md?

A self-reflection system for Claude Code that stores and searches conversations, plans, tasks, and code information locally.

Use it to review past sessions, inspect project-related history, track task outcomes, and search stored development knowledge.

It helps the agent recover useful context from earlier work instead of relying only on the current conversation.

How ramakay/claude-self-reflect configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ramakay/claude-self-reflect. 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/ramakay/claude-self-reflect/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ramakay/claude-self-reflect

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/instructions/ramakay/claude-self-reflect/claude-md/github.svg)](https://agentmods.dev/instructions/ramakay/claude-self-reflect/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ramakay/claude-self-reflect/claude-md"><img src="https://agentmods.dev/badge/instructions/ramakay/claude-self-reflect/claude-md/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/instructions/ramakay/claude-self-reflect/claude-md"><img src="https://agentmods.dev/badge/instructions/ramakay/claude-self-reflect/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,526 This file is loaded in full into every session.

When invoked 2,526 The same file — it is already loaded in full.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.02526	$0.02526
Opus 5.5	$0.01010	$0.01010
Sonnet 5.5	$0.00505	$0.00505
Haiku 4.5	$0.00253	$0.00253

Measured 2mo ago against content hash 165858004a3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

claude-self-reflect CLAUDE.md scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL .../scripts/install.sh | sh # Install v8

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL .../scripts/install.sh | sh # Install v8

CLAUDE.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Self-Reflect v10.1 — Action Guide

Architecture

Single Rust binary (csr-engine). No Python, no Docker, no Qdrant.

csr-engine (44MB)
  ├── MCP server (rmcp, 15 tools)
  ├── Embeddings (FastEmbed, 384-dim, local)
  ├── Search (HNSW, <1ms p95)
  ├── Storage (SQLite)
  ├── AST analysis (ast-grep, 6 languages)
  ├── 6 Claude Code hooks
  └── 3-layer enrichment pipeline

Corpus Sources (v10.1)

Source	Stage	Notes
`~/.claude/projects/*.jsonl`	import (watcher)	primary corpus, `source='conversation'`
`~/.claude/projects/<proj>/<session>/subagents/agent-*.jsonl`	import (watcher, recursive)	`source='sidechain'`, real project from first path component (canonicalized), parent session via `chunk_provenance.source_conv_id`; parent beats child in search dedupe; legacy mis-scoped rows repaired import-side
`~/.claude/tasks/<session>/`	Stop hook	authoritative task state → episode todos/outcome; completed tasks matching still-open verdicts → `resolution_proposals` (human promotes via `csr_resolve`)
`~/.claude/plans/*.md`	daemon (30min)	`source='plan'`, `conversation_id=plan:<slug>`; margin-verified correlation, ambiguous → `_unscoped`; origin conversation always beats plan in search dedupe; decays via mtime timestamp
`~/.codex/sessions/*/rollout-.jsonl`	daemon (30min) + setup	optional vendor adapter, auto-detected; `source='codex_rollout'`; streaming batched ingest; capture-on-appearance (files deleted often); CSR tool payloads filtered via shared predicate
`~/.claude/history.jsonl`	daemon (10min)	`session_registry` spine — never embedded/injected; coverage in `status`
memories / paste-cache	NOT indexed	circularity / privacy — deliberate non-goals

aux_schema_miss:* counters in csr-engine status flag adapter parse failures — check them when Claude Code renames internal formats (TodoWrite→TaskCreate precedent). All reflection-producing pipelines share one sanitizer that suppresses CSR's own tool payloads and hook-injected blocks (csr_tool_blocks_suppressed + csr_hook_wrappers_scrubbed in status) — the self-contamination loop closed in v10.

Read the full file on GitHub · 176 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.

2mo ago First seen · 176 lines · 2,526 tokens per session scan C 165858004a3c

Subscribe to this mod's changes

claude-self-reflect CLAUDE.md is an instructions file published in the GitHub repository ramakay/claude-self-reflect (230 stars, last pushed 4d ago), licensed MIT. It adds 2,526 tokens to every session, about $0.0101 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Memory and context Research ai-memory claude claude-desktop conversation-memory mcp qdrant

claude-self-reflect CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-self-reflect CLAUDE.mdramakay/claude-self-reflect	Instructions file	230	4d ago	MIT	C	2,526	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-self-reflect: Instructions file for Claude Code