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 feigeCode/navop-mcp --skill navopgit clone --depth 1 https://github.com/feigeCode/navop-mcpWrote 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/feigecode/navop-mcp/navop)<a href="https://agentmods.dev/skills/feigecode/navop-mcp/navop"><img src="https://agentmods.dev/badge/skills/feigecode/navop-mcp/navop/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/feigecode/navop-mcp/navop"><img src="https://agentmods.dev/badge/skills/feigecode/navop-mcp/navop.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 | $0.00028 | $0.00989 |
| Opus 5 | $0.00014 | $0.00495 |
| Sonnet 5 | $0.00006 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
navop 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 12d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Navop
Use this Skill when an AI Agent needs to operate Navop resources from a terminal. It keeps a compact workflow in context and loads command help or live schemas only when needed, so the Agent does not carry the complete Navop tool catalog in every turn. This can reduce repeated tool-definition tokens and other context overhead; the amount depends on the client and the number of exposed tools.
The CLI still connects internally to Navop's authenticated loopback Public MCP runtime. Navop remains authoritative for Tool Exposure, permissions, approvals, resource IDs, sessions, results, and audit records. The CLI does not implement SSH, SFTP, terminal, database, Redis, or MongoDB business logic.
The Navop CLI must be installed globally before this Skill can operate resources. Check the command, and install the latest client when it is missing:
navop --version
npm install -g @navop/cli@latest
navop --version
Every Agent-initiated command must include --json. Start with:
navop status --json
Read the status result before choosing a tool:
- If Public MCP is unavailable, ask the user to start Navop and enable Settings > General > MCP > MCP Server.
- Inspect
permissionMode,availableTools,toolGroups,disabledToolGroups, andguidance. - Treat the running host's
tools/listresponse andnavop.runtime_statusresult as authoritative. The npm package and this Skill do not define the host's complete tool set. - If a tool is unavailable, report its exact name and host-reported tool-group state. Ask the user to enable that group under the returned
settingsPathand open the required connection or session. denyblocks mutations.askrequires approval in Navop.allowruns mutations automatically, but still requires clear user intent for destructive actions.- Never claim a capability is enabled merely because the CLI has a convenience command; the live
availableToolslist is authoritative.
Discover the current client and available command surface when needed:
navop --help
navop tool list --json
navop tool schema <tool-name> --json
navop db query --help
navop db exec --help
Prefer a domain command whenever navop --help exposes one for the requested operation. Domain commands are the normal Agent interface; tool call is a low-level fallback, not the default. Use the command's help and validate its flags against the live schema.
For SQL, choose the command by intent:
- Read-only statements use
navop db query. - DDL, DML, scripts, and other write-capable SQL use
navop db exec. - When
navop db execis available, do not replace it withnavop tool call db.exec. - Do not pass onetcli-only policy flags such as
--allow-writeto thenavopCLI. Navop's livepermissionModeand approval flow govern mutations.
Only when no matching domain command is exposed, or when its mapping cannot represent the live input schema, call the exact host tool:
navop tool call <tool-name> --arguments '<json-object-matching-live-schema>' --json
Never invent a command, tool name, flag, argument, resource ID, or session ID from examples in this Skill. Discover resource and session methods from tool list, inspect their schemas, and use only IDs returned by Navop.
What ships with it
4 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.
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.
- 12d ago First seen · 88 lines · 28 tokens per session scan A 0b8da01a2c17
navop is a skill published in the GitHub repository feigeCode/navop-mcp (4 stars, last pushed 16d ago), licensed MIT. It adds 28 tokens to every session and 989 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…