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 skill-templategit 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/skill-template)<a href="https://agentmods.dev/skills/enovatr-labs/specroute/skill-template"><img src="https://agentmods.dev/badge/skills/enovatr-labs/specroute/skill-template/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/skill-template"><img src="https://agentmods.dev/badge/skills/enovatr-labs/specroute/skill-template.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 | $0.00069 | $0.01149 |
| Opus 5 | $0.00034 | $0.00575 |
| Sonnet 5 | $0.00014 | $0.00230 |
| Haiku 4.5 | $0.00007 | $0.00115 |
Grade A, and why
<skill-slug> 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<2–4 sentence overview: what this skill does, what it produces, who uses it.>
When to use
- <Situation 1>
- <Situation 2>
- <Situation 3>
Step 1:
<What this step does. If the skill takes an argument, parse it here. If a key decision is needed, ask the user.>
If the argument is missing or unclear, ask:
- <Question 1>?
- <Question 2>?
Step 2:
| Input | Action | Output |
|---|---|---|
Step 3:
<Continue the guided walkthrough. Validation checkpoints belong here - confirm before destructive actions.>
Step 4: Report
- Files created or modified (paths).
- Frontmatter fields the user must fill in.
- Suggested next agents or commands to invoke.
- Whether matching examples or runtime mirrors need updating.
Don't use for
- <Adjacent operation 1> - use .
- <Adjacent operation 2> - use .
How to fill this template
-
Pick a slug. Lowercase, hyphen-separated. The enclosing directory name is the slug; this file is always
SKILL.md. -
Write the description with triggers. Most important field. Concrete user utterances that should invoke the skill. Pattern:
"Triggers - 'do X', 'help me with Y', 'set up Z'."Cap it at 1024 characters per the standard and front-load the triggers. -
For a Claude Code target,
argument-hintshows the expected argument shape. Use""if no arguments. Use[arg]for required,[arg?]for optional. -
For a Claude Code target,
user-invocable: trueis usually appropriate. Setting it tofalsehides the skill from the invocation menu; it does not block access via the Skill tool, so it is a discoverability control, not an access control. Usedisable-model-invocation: truefor the opposite case (user-only, never auto-selected).
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 · 96 lines · 69 tokens per session scan A 41c1489bd475
<skill-slug> is a skill published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,149 once invoked, about $0.0003 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.
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.
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.
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.
audit-sweep
Reviews a full set of the main loop's outputs together, from a wider vantage than any single one of them, looking specifically for cross-item patterns that a one-item-at-a-time loop is structurally unable to notice.