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 Knuckles-Team/tunnel-manager --skill tunnel-manager-developmentgit clone --depth 1 https://github.com/Knuckles-Team/tunnel-managerWrote 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/knuckles-team/tunnel-manager/tunnel-manager-development)<a href="https://agentmods.dev/skills/knuckles-team/tunnel-manager/tunnel-manager-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/tunnel-manager/tunnel-manager-development/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/knuckles-team/tunnel-manager/tunnel-manager-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/tunnel-manager/tunnel-manager-development.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 | $0.00055 | $0.01288 |
| Opus 5.5 | $0.00022 | $0.00515 |
| Sonnet 5.5 | $0.00011 | $0.00258 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
tunnel-manager-development 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tunnel Manager Development
Use this skill for changes inside the tunnel-manager package. The connector turns an authorized SSH inventory into typed MCP actions for remote commands, operations, system discovery, files, security, and graph ingestion. Keep the HostManager/Tunnel library, action registrations, agent entry point, and packaged resources aligned when a change crosses a boundary.
Repository map
tunnel_manager/tunnel_manager.pyowns HostManager, Tunnel, inventory parsing, SSH policy, and the compatibility CLI.tunnel_manager/remote_execution.pyis the typed alias-only execution seam; it resolves entitlements, secret references, known-host policy, bounded commands, redacted results, and transport failures.tunnel_manager/mcp_server.pyregisters the action-routed MCP surfaces for remote, inventory, operations, system, files, security, and ingest calls.tunnel_manager/__init__.pyis the connector entry point: it binds theConnectortoHostManager/get_clientand the MCP action registrations.tunnel_manager/connector_sources.pydeclares the live source and resource mappings served throughconnector://resources.tunnel_manager/mcp_config.json,tunnel_manager/prompts/,tunnel_manager/skills/, andtunnel_manager/ontology/are the actual packaged resource paths.specs/connector-content/,specs/inventory-authority/, andspecs/sdk/own the repository specifications and generated status evidence.
Before editing
- Start from a real worktree based on the current
origin/mainand identify the owning row underspecs/; status JSON is generated evidence and is never hand-edited. - Trace a changed request from the MCP action and Pydantic model through
HostManager/Tunnel or the remote-execution adapter to its response. Preserve
action names and the stable connector identity
tunnel-manager-mcp. - Use task-local fake transports, inventory files, and actor contexts in tests. Never make live SSH calls, resolve a real secret, or persist a hostname/key.
- Preserve the shared inventory path and secret-reference boundary. Plaintext passwords, raw private keys, and unrestricted host targets do not belong in source, fixtures, logs, or returned results.
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 · 121 lines · 55 tokens per session scan A cd41a552f729
tunnel-manager-development is a skill published in the GitHub repository Knuckles-Team/tunnel-manager (2 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,288 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 2026-10-27.
Other skills, from other repositories
servicenow-api-development
Develop, test, and publish the servicenow-api connector while preserving its typed ServiceNow clients, MCP surface, packaged content, spec evidence, and shared release gates.
gitlab-api-development
Develop, test, gate, and release the GitLab REST and GraphQL connector. Use this skill when changing API mappings, governed MCP tools, authentication, tenant selection, KG ingestion, packaged content, or repository gates.
jellyfin-mcp-development
Develop and validate the jellyfin-mcp connector using its actual agent-connector-sdk entrypoint, Jellyfin API clients, ontology assets, packaged skills, and focused tests. Use this skill for source changes and delivery gates; use the provider skills for live Jellyfin operations.
documentdb-mcp-development
Develop, test, gate, and release the documentdb-mcp connector while preserving its SDK-owned client boundary, action-routed tools, knowledge graph ingestion, packaged resources, and shared publication contracts.
api-connector-builder
Use when writing a client for someone else's REST or GraphQL API: auth flow choice and token refresh, pagination to exhaustion, retry-with-jitter on transient failures only, rate-limit-aware throttling. NOT inbound callbacks (that is webhooks), NOT chaining services (that is automation-flows), NOT designing your own…
linkedin-api
Use when wiring an app to LinkedIn's organic Posts / Community Management API — 3-legged OAuth, publishing text, article or document posts to a member profile or company page, and pulling impressions, engagement and follower stats into a durable feedback record. NOT writing the post copy (that is linkedin-content)…