Borrowing it
Nothing to install: this file belongs to twaldin/flt. 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/twaldin/flt/main/CLAUDE.mdgit clone --depth 1 https://github.com/twaldin/fltWrote 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/instructions/twaldin/flt/claude-md)<a href="https://agentmods.dev/instructions/twaldin/flt/claude-md"><img src="https://agentmods.dev/badge/instructions/twaldin/flt/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.
<a href="https://agentmods.dev/instructions/twaldin/flt/claude-md"><img src="https://agentmods.dev/badge/instructions/twaldin/flt/claude-md.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 | $0.02402 | $0.02402 |
| Opus 5.5 | $0.00961 | $0.00961 |
| Sonnet 5.5 | $0.00480 | $0.00480 |
| Haiku 4.5 | $0.00240 | $0.00240 |
Grade A, and why
flt 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 1mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flt
flt is a multi-CLI agent orchestrator: it makes Claude Code, Codex, Gemini CLI, OpenCode, SWE-agent, and ~7 other AI coding CLIs feel like one tool. A single controller daemon manages tmux-hosted agents across CLIs, normalizes per-CLI quirks behind a CliAdapter interface, and routes messaging, status, worktrees, presets, and YAML workflows through one Unix-socket RPC.
The soul of the project: primitives, not a monolith
flt is a set of primitives a user can compose however they want. spawn, kill, send, list, logs are the primitives. Everything else — presets, workflows, the dynamic DAG, parallel candidates with treatment matrices, the TUI itself — is a composition over those primitives. When designing a new feature, ask first: "is this just a new way to compose spawn/send/kill?" If yes, build it as a composition (a YAML workflow step, a preset field, a TUI command). Only carve out a new primitive when no composition can express it. This is the lens for every non-trivial change here.
Architecture
- Single-writer controller. A daemon (
src/controller/server.ts) is the only writer to~/.flt/state.json. Every CLI command (flt spawn,flt send, …) and the TUI talk to it over a Unix socket at~/.flt/controller.sock. The TUI is a pure reader; closing/reopening it never affects running agents. - tmux as the agent host. Each agent runs in its own detached tmux session.
src/tmux.tswrapsnew-session,pipe-panelogging, key delivery, and pane capture. ANSI output from agents is captured raw and re-parsed in the TUI. - Worktree-per-agent isolation.
src/worktree.tscreates aflt/<name>branch and worktree undertmpdir()so concurrent agents don't trample each other's git state.--no-worktreeopts out. - Per-CLI adapters.
src/adapters/definesCliAdapter(spawn args, instruction filename, ready-state detection, dialog auto-approval, status detection). Most adapters delegate to@twaldin/harness-tsfor shared detection logic; flt adds the spawn/lifecycle/dialog-bypass on top. - Status by polling pane content. No agent SDKs are wired up.
src/controller/poller.tsrunstmux capture-pane, feeds the buffer toadapter.detectStatus, and writes status transitions back to state. Workflow advancement, ephemeral cleanup, and TUI status colors all hang off this single transition signal. - Instructions are projected, not owned.
src/instructions.ts(delegating to@twaldin/harness-ts) prepends a block delimited byflt:start/flt:endto the adapter's instruction file (CLAUDE.md,AGENTS.md,GEMINI.md, etc.) and restores the original on kill. flt never owns the file outside its markers.
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.
- 1mo ago Changed · +1 lines · +35 tokens per session 365e15cca543
- 1mo ago First seen · 92 lines · 2,367 tokens per session scan A 6d7efff63d4c
flt CLAUDE.md is an instructions file published in the GitHub repository twaldin/flt (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,402 tokens to every session, about $0.0096 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 2026-08-31.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.