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 scaffold-artifactgit 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/scaffold-artifact)<a href="https://agentmods.dev/skills/enovatr-labs/specroute/scaffold-artifact"><img src="https://agentmods.dev/badge/skills/enovatr-labs/specroute/scaffold-artifact/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/scaffold-artifact"><img src="https://agentmods.dev/badge/skills/enovatr-labs/specroute/scaffold-artifact.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 | $0.00087 | $0.01098 |
| Opus 5 | $0.00044 | $0.00549 |
| Sonnet 5 | $0.00017 | $0.00220 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
scaffold-artifact 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold Artifact
Interactive scaffolding for SpecRoute contributors. Reduces "where does this file go and what frontmatter does it need" friction.
When to use
- Starting a new PRD, spec triplet, ADR, agent, skill, command, hook, or prompt
- Adding a new vendor runtime layout under
runtimes/ - Bootstrapping the worked example in
examples/sample-project/
Step 1: Parse the argument
Argument shape: [artifact-type] [name] [vendor?]. Examples:
prd notification-preferencesspec-triplet user-searchagent backend-engineerskill manifest-auditcommand claude /run-checkshook claude pre-commit-sanitizeruntime cursor
If the argument is missing or unclear, ask the user:
- Which artifact type? (PRD / lightweight PRD / SRS / spec triplet / feature spec / ADR / agent / skill / command / hook / prompt / runtime)
- Name (slug, lowercase-hyphenated)?
- If vendor-specific (command, hook, runtime, prompt): which vendor (claude / codex / gemini / kiro / cursor / devin)?
Step 2: Resolve target path and template
Use the artifact-type → location mapping:
| Type | Target | Template |
|---|---|---|
prd |
prds/active/<name>.md |
prds/templates/prd-template.md |
lightweight-prd |
prds/active/<name>.md |
prds/templates/lightweight-prd-template.md |
srs |
prds/active/<name>-srs.md |
prds/templates/platform-srs-template.md |
spec-triplet |
specs/examples/<name>/{requirements,design,tasks}.md |
specs/templates/{requirements,design,tasks}-template.md |
feature-spec |
specs/examples/<name>.md |
specs/templates/feature-spec-template.md |
adr |
specs/examples/adr-<NNN>-<name>.md |
specs/templates/architecture-decision-record.md |
agent |
agents/examples/<name>.md |
agents/agent-template.md |
skill |
skills/examples/<name>/SKILL.md |
skills/skill-template/SKILL.md |
command (claude) |
commands/examples/<name>.claude.md |
commands/command-template.claude.md |
command (gemini) |
commands/examples/<name>.gemini.toml |
commands/command-template.gemini.toml |
hook (claude) |
hooks/claude/scripts/<name>.sh + entry in hooks/claude/hooks.template.json |
hooks/claude/hooks.template.json |
hook (kiro) |
hooks/kiro/examples/<name>.json |
(existing example) |
prompt |
prompts/<vendor>/<name>.md or prompts/shared/<name>.md |
prompts/shared/task-prompt-template.md |
runtime |
runtimes/.<vendor>/ |
(mirror nearest existing runtime) |
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 · 84 lines · 87 tokens per session scan A 19daa6aab0e9
scaffold-artifact is a skill published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,098 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.