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 Enovatr-Labs/SpecRoute --skill add-vendorgit clone --depth 1 https://github.com/Enovatr-Labs/SpecRouteWrote 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/enovatr-labs/specroute/add-vendor)<a href="https://agentmods.dev/skills/enovatr-labs/specroute/add-vendor"><img src="https://agentmods.dev/badge/skills/enovatr-labs/specroute/add-vendor/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/enovatr-labs/specroute/add-vendor"><img src="https://agentmods.dev/badge/skills/enovatr-labs/specroute/add-vendor.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 | $0.00073 | $0.01115 |
| Opus 5 | $0.00036 | $0.00558 |
| Sonnet 5 | $0.00015 | $0.00223 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
add-vendor 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Vendor
Adds a new agent CLI vendor to SpecRoute end-to-end. The supported vendor matrix in the README is the contract - adding a vendor means a new column, not a fork.
When to use
- A new agent CLI tool (e.g. Aider, Continue, Open Interpreter, etc.) needs SpecRoute support
- Updating SpecRoute to track a vendor's new feature (e.g. a vendor adds slash-command support)
Step 1: Gather vendor information
Ask the user (or parse from the argument):
- Vendor name (slug, lowercase): used as
runtimes/.<vendor>/ - Runtime directory convention: where does this vendor expect its config? (
.<vendor>/,.config/<vendor>/, etc.) - Root context file convention: does this vendor read a top-level
<VENDOR>.md? Does it delegate to AGENTS.md? - Skills support: does the vendor support skills? In what shape (folder-per-skill
SKILL.md? Single config file?)? - Agents support: same question for agents.
- Commands support: slash commands? In what shape?
- Hooks support: event-triggered automation? Trigger types?
- MCP support: which file? What format?
- Rules support: where does the vendor read engineering rules?
Step 2: Scaffold the runtime layout
Create runtimes/.<vendor>/ with:
README.md- what each subdir contains, the frontmatter contracts, drop-in instructions- One subdir per supported feature (skills/, agents/, commands/, hooks/, rules/)
- Config template files with
.template.<ext>suffix (e.g.settings.template.json) - For features the vendor doesn't support, do NOT create empty dirs - document the gap in the README
Step 3: Update the supported vendor matrix
Edit the matrix table in all four mirror locations (keep them lock-step):
README.mdAGENTS.mdwiki/Vendor-Matrix.mdagentic-docs/agent-cli-integrations.md
Add the new vendor row, naming the vendor's native shape for each capability (skills, agents, commands, hooks, MCP). Also update the context-file table in agentic-docs/multi-vendor-context-files.md if the vendor reads a root context file.
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 · 93 lines · 73 tokens per session scan A 31e0951e6669
add-vendor is a skill published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,115 once invoked, about $0.0004 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
file-a-task
File work into nohuman (taskadd) and check on it (taskstatus) via the nohuman MCP bridge, instead of doing the work inline.
merge-aliases
Folds two surface names for the same backend system into one canonical entity, keeping every original mention individually retrievable, and refuses to merge pairs that only share spelling.
anchor-and-lock
Consults a check that sits outside the loop system before finalizing any decision the frozen facts bear on, and refuses every attempt by a loop to rewrite a node marked frozen, regardless of how convergent the loop's own reasoning looks.
query-graph
Loads schema.sql into a local SQLite file, then answers availability and provenance questions against the nodes/edges tables with real SQL instead of re-reading source material.
build-subgraph
Traverses a full graph and returns a bounded subgraph around one target node -- its depth-bounded dependencies plus any disputed claims attached to it -- while proving everything else was left out.
arbitrate-collision
Detects when two loops have proposed conflicting writes to the same node and field at close to the same time, applies a stated priority rule to accept exactly one, and records the rejected write with the reason it lost.