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 ashishthomas2202/tdoms-mcp --skill tdoms-mcp-routinggit clone --depth 1 https://github.com/ashishthomas2202/tdoms-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/ashishthomas2202/tdoms-mcp/tdoms-mcp-routing)<a href="https://agentmods.dev/skills/ashishthomas2202/tdoms-mcp/tdoms-mcp-routing"><img src="https://agentmods.dev/badge/skills/ashishthomas2202/tdoms-mcp/tdoms-mcp-routing/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/ashishthomas2202/tdoms-mcp/tdoms-mcp-routing"><img src="https://agentmods.dev/badge/skills/ashishthomas2202/tdoms-mcp/tdoms-mcp-routing.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 | $0.00115 | $0.01462 |
| Opus 5 | $0.00057 | $0.00731 |
| Sonnet 5 | $0.00023 | $0.00292 |
| Haiku 4.5 | $0.00012 | $0.00146 |
Grade A, and why
tdoms-mcp-routing 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 11d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TD/OMS MCP Routing
Use the standalone MCP as the primary automation surface. It talks to the configured TD/OMS REST server and does not control VS Code or require an Octo session.
Load References Deliberately
- Read references/workflow-playbooks.md before performing a domain workflow such as checkout, promote, source save, compile, completion, ratification, branch work, or conflict handling.
- Read references/tool-and-extension-map.md when selecting tools, comparing the standalone MCP with Octo, or checking whether a capability is core-only, full-profile, UI-only, or unsupported.
- Read references/tdoms-domain-and-sources.md when terminology, lifecycle semantics, source authority, or version differences matter.
Establish Runtime Context
- Inspect the tools actually available in the current agent session. Runtime tool schemas override this skill if names or inputs differ.
- Call
tdoms_list_connections. - If exactly one connection exists, omit
connectionIdwhere the schema permits and calltdoms_get_current_context. - If several connections exist, select only from the returned profiles. Ask the user to choose when the request does not identify one.
- If no connection exists, direct the user to save and test one through
tdoms-mcp ui. Never request a password, token, or certificate contents in chat. - Treat
user.programmerIdfrom current context as the default identity for "my" records. Do not ask for a programmer ID unless the user is reassigning work, selecting another programmer, or the server cannot derive one.
Choose the Surface
- Prefer the seven
coretools for portable agent workflows and small tool budgets. - Use
tdoms_discover_optionsfor both choices and structured reads that replace Octo views. - Use
tdoms_plan_workflowandtdoms_execute_workflowwhenever the requested mutation appears intdoms_list_capabilities. - Use a
fullnamed tool when no core capability exists or when a typed tool gives safer inputs, richer diagnostics, or a complete read workflow. - Use Octo tools only when the user explicitly needs an Octo panel/editor or when the standalone MCP lacks the required TD/OMS or Octo-cloud operation.
- Do not use
tdoms_call_apiuntil named and planned tools have been ruled out and the endpoint and body are documented for the connected TD/OMS version.
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.
- 11d ago First seen · 90 lines · 115 tokens per session scan A ec5d10ee0c73
tdoms-mcp-routing is a skill published in the GitHub repository ashishthomas2202/tdoms-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 1,462 once invoked, about $0.0006 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
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
gsd-complete-milestone
Archive completed milestone and prepare for next version.
operating-github-cli
Default GitHub skill for the action agent. Use githubcli for any GitHub request — create/list/view/close issues and PRs, assign, labels, repos, releases, checks, github.com/owner/repo URLs, or gh api. Prefer over shellrun/!gh. Run these with githubcli in the current agent turn.
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
testdino-releases
Use when the user wants to browse, inspect, create, or update releases/milestones in a TestDino project. Covers listreleases, getrelease, createrelease, and updaterelease. Accepts counter-style IDs like MS-12.
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.