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-operationsgit 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-operations)<a href="https://agentmods.dev/skills/knuckles-team/tunnel-manager/tunnel-manager-operations"><img src="https://agentmods.dev/badge/skills/knuckles-team/tunnel-manager/tunnel-manager-operations/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-operations"><img src="https://agentmods.dev/badge/skills/knuckles-team/tunnel-manager/tunnel-manager-operations.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 | $0.00057 | $0.00319 |
| Opus 5 | $0.00028 | $0.00160 |
| Sonnet 5 | $0.00011 | $0.00064 |
| Haiku 4.5 | $0.00006 | $0.00032 |
Grade A, and why
tunnel-manager-operations 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 10d 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.
This is a copy
81% identical to gitlab-api-operations — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Tunnel Manager Operations
Use the provider's governed MCP tools through GraphOS delegation.
Workflow
- Establish the verified GraphSession and tenant before discovery or retrieval.
- Discover the current condensed tool surface; never assume a stale tool name or schema.
- Prefer read-only inspection first. For changes, present impact and use the provider's dry-run or preview mode when available.
- Execute mutations as fenced WorkItems so retries remain idempotent and auditable.
- Ingest source data only through the signed connector preset and ChangeEnvelope path.
- Verify the durable result and its trace/evidence before reporting completion.
Safety contract
- Never persist credentials, endpoints, raw personal identifiers, hostnames, or local paths.
- Resolve TLS trust and verification from environment/configuration; never hardcode bypasses.
- Treat unknown ACL, tenant, schema, or tool-contract state as a hard failure.
- Require explicit approval for destructive, externally visible, or irreversible actions.
- Keep runtime traces policy-scoped and privacy-sanitized.
Specialized workflows
Read the workflow catalog only when the request needs a provider-specific procedure, parameter map, script, or reference asset.
What ships with it
2 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.
- 10d ago First seen · 34 lines · 57 tokens per session scan A e87c7c8d4934
tunnel-manager-operations is a skill published in the GitHub repository Knuckles-Team/tunnel-manager (2 stars, last pushed 13d ago), licensed MIT. It adds 57 tokens to every session and 319 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 81% identical to gitlab-api-operations, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
memory-audit-discoverability
A review guide for checking whether stored memories can be found at the right time. It focuses on where memories are attached, when they are triggered, whether aliases are missing, and whether a parent has too many children.
memory-audit-pattern-extraction
A method for investigating repeated mistakes by comparing related memories and checking whether an earlier reminder failed. It looks at where the reminder was stored, when it was created, and whether it was strong enough to prevent the mistake.
repo-cve-findings
Resolve a GitHub repository in the security graph and list the CVEs recorded against it, confirming from the graph's dependency data which vulnerable versions are actually installed. Produces the finding set that a reachability review then judges against the source.
github-org-security-overview
Guide an agent through a GitHub organization security investigation using the githubsecurity toolset and produce a prioritized executive summary.
review-source-dependencies
Inspect a repository and verify how one package reaches a target dependency.
verify-packaged-assets
Verify that a packaged reference can be read and a packaged script can execute in the conversation sandbox.