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.
npx agentmods add instructions/estebanforge/fuse-agents/agents-mdgit clone --depth 1 https://github.com/EstebanForge/fuse-agentsWhat 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 | $0.01149 | $0.01149 |
| Opus 5 | $0.00575 | $0.00575 |
| Sonnet 5 | $0.00230 | $0.00230 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
fuse-agents AGENTS.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 2d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview
This is a cross-shell plugin (Bash & Zsh) that automatically fuses AI assistant configuration files (CLAUDE.md, GEMINI.md) into a unified AGENTS.md file with intelligent symlink management. The plugin provides automatic detection, smart merging, and different handling for different AI assistants.
Key Architecture
Shell Compatibility Layer
The plugin detects the current shell (Bash/Zsh/unknown) and adapts behavior:
SHELL_TYPEvariable determines shell-specific featuresarray_join()function handles cross-shell array operations- Different hook mechanisms: Zsh uses
chpwd, Bash usesPROMPT_COMMAND
Core Processing Pipeline
- Detection:
_fuse_auto_detect()triggers on directory changes - Processing:
_fuse-agents()handles individual directories - File Handling:
_handle_ai_file()manages individual AI assistant files - Conflict Resolution: Interactive prompts using
gum(if available) or fallback text prompts
Critical Design Decisions
- CLAUDE.md: Always symlinked to AGENTS.md (Claude requires symlink)
- GEMINI.md: Always symlinked to AGENTS.md (same as CLAUDE.md)
- Auto-detection: Triggers for both CLAUDE.md and GEMINI.md files
- Merge Strategy: Creates timestamped backups and structured merges
- Conditional Symlinks: Symlinks are only created for files that existed originally
Common Development Tasks
Testing Plugin Functionality
# Test basic fusing
mkdir -p /tmp/test-fuse
cd /tmp/test-fuse
echo "# Claude instructions" > CLAUDE.md
echo "# Gemini instructions" > GEMINI.md
source /path/to/fuse-agents.plugin.sh
fuse-agents-auto
# Test recursive processing
mkdir -p ~/test-projects/{proj1,proj2}
echo "# Claude proj1" > ~/test-projects/proj1/CLAUDE.md
echo "# Gemini proj2" > ~/test-projects/proj2/GEMINI.md
fuse-agents-recursive ~/test-projects
Installation Testing
# Test installer script
./install.sh
# Verify installation
type fuse-agents
fuse-agents --help
# Test auto-hooks by changing directories
cd ~/project-with-CLAUDE.md
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.
- 2d ago First seen · 136 lines · 1,149 tokens per session scan A 15002b464556
fuse-agents AGENTS.md is an instructions file published in the GitHub repository EstebanForge/fuse-agents (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,149 tokens to every session, about $0.0057 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.