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 skills add qf-studio/navigator --skill nav-loopgit 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/skills/qf-studio/navigator/nav-loop)<a href="https://agentmods.dev/skills/qf-studio/navigator/nav-loop"><img src="https://agentmods.dev/badge/skills/qf-studio/navigator/nav-loop/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/skills/qf-studio/navigator/nav-loop"><img src="https://agentmods.dev/badge/skills/qf-studio/navigator/nav-loop.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 | $0.00043 | $0.04152 |
| Opus 5.5 | $0.00017 | $0.01661 |
| Sonnet 5.5 | $0.00009 | $0.00830 |
| Haiku 4.5 | $0.00004 | $0.00415 |
Grade A, and why
nav-loop 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 21d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- nav-loop — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 591 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Navigator Loop Skill
Execute tasks iteratively until completion with structured signals, stagnation detection, and dual-condition exit gates.
Why This Exists
Traditional AI coding requires manual "keep going" prompts. Navigator Loop provides:
- Structured completion signals (NAVIGATOR_STATUS block)
- Dual-condition exit gate (heuristics + explicit signal)
- Stagnation detection (circuit breaker for stuck loops)
- Progress visibility (phases: INIT → RESEARCH → IMPL → VERIFY → COMPLETE)
Based on Ralph's autonomous loop innovations, adapted for Navigator's context-efficient architecture.
When to Invoke
Auto-invoke when:
- User says "run until done", "keep going until complete"
- User says "iterate until finished", "autonomous mode"
- User says "loop mode", "don't stop until done"
- Task document has
loop_mode: true
DO NOT invoke if:
- Single-step task (no iteration needed)
- User says "just do this once"
- Already in loop mode (prevent nested loops)
- User explicitly disabled loop mode
Configuration
Loop mode settings in .agent/.nav-config.json:
{
"loop_mode": {
"enabled": false,
"max_iterations": 5,
"stagnation_threshold": 3,
"exit_requires_explicit_signal": true,
"show_status_block": true,
"iteration_approval": "none",
"periodic_interval": 3,
"never_pause_on_stagnation": false,
"stagnation_diversify_strategy": "combine"
}
}
Core options:
enabled: Default state for new tasksmax_iterations: Hard cap to prevent infinite loops (1-20)stagnation_threshold: Same-state count before pause (2-5)exit_requires_explicit_signal: Require EXIT_SIGNAL alongside heuristicsshow_status_block: Render NAVIGATOR_STATUS each iteration
Autonomous / overnight options (v6.2.2+):
iteration_approval: When to prompt the user for accept/reject between iterations."none"(default) — never prompt; loop runs uninterrupted"strict"— prompt after every iteration"periodic"— prompt every N iterations (where N =periodic_interval, default 3)
periodic_interval: Wheniteration_approval == "periodic", the cadence of prompts. Default 3 (every 3rd iteration). Set higher for less frequent check-ins on long overnight runs (e.g., 5 or 10).never_pause_on_stagnation: Iftrue, stagnation triggers auto-diversification instead of anAskUserQuestionpause. Required for true overnight runs. Inspired by karpathy/autoresearch's NEVER STOP directive.stagnation_diversify_strategy: Which recovery to attempt whennever_pause_on_stagnationfires."combine"— combine previous near-misses / partially-met indicators"radical"— try a substantially different approach (re-architect, swap library)"reread"— re-read the in-scope task/system docs for missed signals
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- functions/exit_gate.py 4.6 KB runs code
- functions/phase_detector.py 5.8 KB runs code
- functions/stagnation_detector.py 6.4 KB runs code
- functions/status_generator.py 4.5 KB runs code
- functions/test_exit_gate.py 9.2 KB runs code
- functions/test_phase_detector.py 9.3 KB runs code
- functions/test_stagnation_detector.py 10 KB runs code
- functions/test_status_generator.py 11 KB runs code
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.
- 21d ago First seen · 591 lines · 43 tokens per session scan A 12b3b09c133a
nav-loop is a skill published in the GitHub repository qf-studio/navigator (355 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 4,152 once invoked, about $0.0002 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 2026-09-25.
Other skills, from other repositories
nav-install-multi-claude
DEPRECATED. The multi-Claude orchestration scripts are deprecated in favor of native Claude Code Workflows; no installation is needed. Auto-invokes on "install multi-Claude workflows", "set up multi-Claude", "enable parallel execution" to explain the deprecation.
nav-multi
DEPRECATED. Multi-Claude shell orchestration is superseded by native Claude Code Workflows. Auto-invokes on "run multi-agent workflow", "parallel agents for", "multi-claude for", "spawn agents for" to redirect the user to the native Workflow and Agent tools.
product-design
Automates design review, token extraction, component mapping, and implementation planning. Reduces design handoff from 6-10 hours to 5 minutes via direct Figma MCP integration. Auto-invoke when user mentions design review, Figma mockup, or design handoff.
social-media-post
Generate optimized social media posts for Threads, X (Twitter), and LinkedIn. Analyzes platform algorithms, applies best practices, and creates engaging content tailored to each platform. Local skill for Navigator marketing only.
nav-loop
Run tasks until complete with structured completion signals. Auto-invoke when user says "run until done", "keep going until complete", "iterate until finished", "loop mode", "autonomous mode".
nav-skill-creator
Analyze codebase patterns and create custom skills for repetitive workflows. Use when project needs automation or pattern enforcement. Auto-invoke when user says "create a skill for...", "automate this workflow", or "we keep doing X manually".