Borrowing it
Nothing to install: this file belongs to qf-studio/navigator. 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/qf-studio/navigator/main/CLAUDE.mdgit clone --depth 1 https://github.com/qf-studio/navigatorWrote 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/qf-studio/navigator/claude-md)<a href="https://agentmods.dev/instructions/qf-studio/navigator/claude-md"><img src="https://agentmods.dev/badge/instructions/qf-studio/navigator/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/qf-studio/navigator/claude-md"><img src="https://agentmods.dev/badge/instructions/qf-studio/navigator/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 | $0.05653 | $0.05653 |
| Opus 5.5 | $0.02261 | $0.02261 |
| Sonnet 5.5 | $0.01131 | $0.01131 |
| Haiku 4.5 | $0.00565 | $0.00565 |
Grade A, and why
navigator CLAUDE.md scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
fires there unless `auto_update.curl_fallback: true` repeats the same GET through `curl` Copies of this mod
1 near-identical copy found in the catalogue:
- navigator CLAUDE.md — 92% identical, 146 lines differ
How it starts
The opening of the file, as written. The whole thing — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Navigator: Finish What You Start
Sessions that last. AI that learns. Features that ship.
Why This Exists
The problem: AI coding sessions crash at exchange 5-7. Context window fills with documentation you never use.
Navigator's solution: Context engineering — load what you need, when you need it. 150k → 12k tokens (92% reduction).
Result: Sessions go 20+ exchanges. Features actually ship.
Proven: OpenTelemetry-verified, not estimates. Session efficiency scores 94/100.
Version history: see CHANGELOG.md for the full release log, or releases/ for per-version notes.
Core Principle
Context engineering beats bulk loading.
Not "load everything just in case." Not "better safe than sorry." Strategic loading saves 92% of context for actual work.
New to this approach? Read the philosophy:
.agent/philosophy/CONTEXT-EFFICIENCY.md- Why Navigator exists.agent/philosophy/ANTI-PATTERNS.md- Common mistakes (upfront loading, etc.).agent/philosophy/PATTERNS.md- What works and why
Navigator Runtime (v8)
Navigator's workflow is enforced by a hook runtime, not by prose in this file. As of v8.0.0
that runtime is a Claude Code mod: one in-process TypeScript module
(hooks/hooks.json → hooks/mod/register.tsx) that runs every op on Claude Code
2.1.287 or newer. The v7 Python dispatcher (hooks/nav_dispatch.py →
nav_hook_lib.runtime) stays registered as the fallback: on older Claude Code, where an
organization's policy blocks mods, or when an op crashes three times in a session, Python runs
that op instead. The mod announces what it owns in NAVIGATOR_MOD_OWNS; the Python dispatcher
skips owned ops in one place and exits immediately when it owns nothing to do. Both share one
state file, .agent/.nav-runtime-state.json, so an op handed across sees the same state.
Each behavior is an op with a config off-switch in .agent/.nav-config.json:
| Behavior | Op | Mod event | Off-switch |
|---|---|---|---|
| Workflow gating | prompt_gate | prompt.submit |
workflow_enforcer_hook.enabled, .strict_block |
| Tier-1 instant answers | prompt_tier1 | prompt.submit |
tier1.enabled, per rule via tier1.rules |
| Reply modes (ADHD shape, STE sentences) | prompt_modes | prompt.submit |
reply_modes.enabled; per mode <key>_mode.enabled, <key> mode on/off or <key>_mode.on |
| Intent briefs on ambiguous prompts | prompt_brief | prompt.submit |
brief_hook.enabled |
| Repeated-Read guard | read_guard | tool.call (Read) |
read_guard_hook.enabled, .strict_block |
| Session context injection | session_start | classic.SessionStart |
session_start_hook.enabled |
| Workflow/loop state recording | stop_state | classic.Stop |
workflow_state_hook.enabled |
| Completion gate (forced continuation) | stop_completion | classic.Stop |
stop_completion.continue_enabled |
| Reject log (one JSONL line per refusal) | runner (lib) | every blocking op result | reject_log.enabled |
| Context markers around compaction | compact_marker | classic.PreCompact / PostCompact |
compact_hook.enabled |
| Typed judge behind the prompt scorers | judge (lib) | — | judge.enabled |
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.
- today Changed · +2 lines · +45 tokens per session e73813455313
- 6d ago Changed 7349d411a716
- 8d ago Changed · +5 lines · +120 tokens per session 79aa00cdf328
- 10d ago Changed · +15 lines · +315 tokens per session 2169727424ca
- 11d ago Changed · +16 lines · +401 tokens per session 6f5ade4ec973
- 14d ago Changed · +18 lines · +345 tokens per session af1c81f3325a
- 16d ago Changed · +3 lines · +49 tokens per session 920fdc27c227
- 20d ago First seen · 400 lines · 4,378 tokens per session scan A e7b61d0d142f
navigator CLAUDE.md is an instructions file published in the GitHub repository qf-studio/navigator (355 stars, last pushed today), licensed MIT. It adds 5,653 tokens to every session, about $0.0226 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.
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.
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.
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).