FusionAL-Recall: Instructions file for Claude Code

CLAUDE.md

FusionAL-Recall CLAUDE.md is an instructions file for Claude Code from JRM-FusionAL/FusionAL-Recall. It costs 738 tokens per session, scanned A, original, MIT.

Project-specific instructions for Claude Code in the FusionAL-Recall repository. They describe the project, its configuration, and a process for searching previously solved issues before debugging.

In plain words
What is it for?
They guide environment configuration, Notion data synchronization, and searches of the solved-issues registry during debugging.
Why use it?
They keep coding-agent work aligned with the repository’s setup and help avoid repeating investigations that may already have answers.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is JRM-FusionAL/FusionAL-Recall's own configuration. It tells Claude Code how to work on FusionAL-Recall 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 FusionAL-Recall configures →

Reuse

Borrowing it

Nothing to install: this file belongs to JRM-FusionAL/FusionAL-Recall. 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/JRM-FusionAL/FusionAL-Recall/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/JRM-FusionAL/FusionAL-Recall

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 FusionAL-Recall CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jrm-fusional/fusional-recall/claude-md.svg)](https://agentmods.dev/instructions/jrm-fusional/fusional-recall/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jrm-fusional/fusional-recall/claude-md"><img src="https://agentmods.dev/badge/instructions/jrm-fusional/fusional-recall/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 738 This file is loaded in full into every session.
When invoked 738 The same file — it is already loaded in full.
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 $0.00738 $0.00738
Opus 5 $0.00369 $0.00369
Sonnet 5 $0.00148 $0.00148
Haiku 4.5 $0.00074 $0.00074

Measured 7d ago against content hash 19d1302b81a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

FusionAL-Recall CLAUDE.md 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.

CLAUDE.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — fusional-recall

Repo-specific instructions for Claude Code sessions inside this project. Global rules in ~/.claude/CLAUDE.md apply first.

Project Identity

fusional-recall is a standalone FastMCP server providing semantic search over the solved-issues registry. The Notion Solved Issues DB is canonical (data source 836a9fe2-738d-4fdf-90a5-4364e1b36f1f); recall.db is a derived index synced from it at startup and hourly. SOLVED-ISSUES.md remains only as an empty-DB seed fallback. Embeddings via fastembed (ONNX). See docs/superpowers/specs/2026-07-07-notion-sync-design.md.

Port: 8107 DB: ./recall.db (local) or /data/recall.db (Docker)

Config (env / .env in repo root — never commit .env)

Var Default Meaning
NOTION_TOKEN unset Notion integration token; unset disables sync
NOTION_DATA_SOURCE_ID 836a9fe2-...36f1f Solved Issues data source
NOTION_SYNC_INTERVAL 3600 Seconds between background syncs; 0 disables

Recall Protocol (this project)

Before debugging any error in this repo:

  1. State "Recall check: searching solved issues for "
  2. Call the recall MCP tool (localhost:8107) — or query the Notion Solved Issues DB
  3. State outcome

Auto-Log Triggers (this project)

Log a new SI entry whenever:

  • migration regex fails to parse a valid SI block
  • embedding model fails to load (model name drift, network, HW)
  • cosine similarity returns unexpected values (float packing bug)
  • FastMCP version change breaks tool registration
  • DB path or env var silently falls back to wrong default

Dev Commands

# Install deps (WSL or native Python)
python -m venv venv && source venv/bin/activate
pip install -r requirements.txt

# Run tests
pytest tests/ -v --cov=recall --cov-report=term-missing

# Start server (reads .env)
python -m recall.server

# Docker
docker compose up --build

MCP Tool Summary

Tool Purpose
recall Semantic search — returns ranked SI list
remember Log new SI entry to Notion (canonical) + local index
list_recent List N newest issues
verify Fetch specific issue by SI-ID
get Alias for verify

Read the full file on GitHub · 76 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. 7d ago First seen · 76 lines · 738 tokens per session scan A 19d1302b81a5

Subscribe to this mod's changes

FusionAL-Recall CLAUDE.md is an instructions file published in the GitHub repository JRM-FusionAL/FusionAL-Recall (0 stars, last pushed yesterday), licensed MIT. It adds 738 tokens to every session, about $0.0037 per session on Opus 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens