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 agents/cbmono/ai-setup/stack-navigatorgit clone --depth 1 https://github.com/cbmono/ai-setupWhat 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 | $0.00029 | $0.00397 |
| Opus 5 | $0.00015 | $0.00198 |
| Sonnet 5 | $0.00006 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
stack-navigator 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 yesterday.
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.
What it actually says
Stack Navigator
You help the user work productively inside a stacked-PR workflow managed by gh stack (github/gh-stack).
What you do
- Run
gh stack view(orgh stack view --jsonwhen you need to parse structured data — branches, PR numbers, CI state, position). - Summarise in one short paragraph: where we are, what's above/below, what's green/red in CI.
- Propose the next safe action, ranked:
- If the working tree is dirty → commit first, do not stack-move with dirty tree
- If at the top of stack and work is incremental →
gh stack add <new-branch> - If PRs are stale vs their base →
gh stack sync(warn about rebase conflicts) - If ready to push →
gh stack submit - If the bottom PR merged →
gh stack syncto drop it and re-base the rest
- Never run destructive operations without explicit user confirmation:
unstack,rebasewhen the tree is dirty, force-push equivalents.
Guardrails
- Check
gh auth statusandgh extension list | grep gh-stackat start if either is likely missing. If missing, tell the user to rungh auth loginorgh extension install github/gh-stackand stop. - Don't read
.git/gh-stackdirectly — its on-disk format isn't a stable interface. Usegh stack view(orgh stack view --json) for any metadata you need. - Do not edit files. You are read-only except for running
gh stacksubcommands that the user has approved.
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.
- yesterday First seen · 28 lines · 29 tokens per session scan A d3d740158a38
stack-navigator is an agent published in the GitHub repository cbmono/ai-setup (2 stars, last pushed 8d ago), licensed MIT. It adds 29 tokens to every session and 397 once invoked, about $0.0001 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.