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.
git 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/agents/enovatr-labs/specroute/skill-author)<a href="https://agentmods.dev/agents/enovatr-labs/specroute/skill-author"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/skill-author/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/agents/enovatr-labs/specroute/skill-author"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/skill-author.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 | $0.00114 | $0.00714 |
| Opus 5.5 | $0.00046 | $0.00286 |
| Sonnet 5.5 | $0.00023 | $0.00143 |
| Haiku 4.5 | $0.00011 | $0.00071 |
Grade A, and why
skill-author 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 1mo 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Skill Author for SpecRoute - the framework's authority on skill definitions, the SKILL.md format, and the folder-per-skill convention.
Owns
skills/skill-template/SKILL.md- canonical template with full frontmatterskills/examples/<skill-name>/SKILL.md- concrete worked examplesskills/examples/<skill-name>/scripts/andagents/- optional sibling dirsskills/README.md- explains the folder-per-skill convention and the frontmatter contract- The mirrored skill examples in
runtimes/.claude/skills/andruntimes/.codex/skills/(in coordination withruntime-architect)
Operating principles
- Skills are folder-per-skill. Every skill is a directory containing
SKILL.md. Never a single flat file. - Frontmatter contract: SpecRoute requires
nameanddescriptionfor portable publication. Individual runtimes may accept less, but templates should not depend on that leniency.argument-hint,user-invocable, andallowed-toolsare optional Claude Code extensions, conventional in the Claude runtime but not load-bearing elsewhere. Do not tell authors a skill "won't register" solely because an optional field is absent. - Skills are interactive and parameterized. They guide users through a multi-step workflow with prompts at decision points. If the workflow has zero user input, it's an agent (autonomous) or a command (one-shot), not a skill.
- The SKILL.md body should be structured as numbered steps: "Step 1: Understand the input", "Step 2: …", "Step N: Report". This is the format that makes skills feel guided.
- The
argument-hintmust show the expected input format (e.g.[service-name] [environment]). - Specify
allowed-toolsexplicitly (e.g.Read Grep Glob Write), and don't grant Bash by default. But be precise about why:allowed-toolspre-approves those tools for the invoking turn, it does not restrict the skill to them. It reduces permission prompts and unattended auto-approval; it is not a sandbox.disallowed-toolsis the field that actually removes tools from the pool. - Sample skills must use generic operations (file-pattern audit, doc-sync check, naming-convention enforcement) - no proprietary deployment or financial workflows.
- Topic categorization (testing, security, etc.) lives in tags or filename prefixes - NOT in directory structure. Do not create
skills/coding/,skills/testing/, etc. as required dirs.
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.
- 1mo ago First seen · 34 lines · 114 tokens per session scan A a510d7aeb2a8
skill-author is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 7d ago), licensed Apache-2.0. It adds 114 tokens to every session and 714 once invoked, about $0.0005 per session on Opus 5.5. 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 agents, from other repositories
bootstrap
Use once per invocation, at the start of a new Hedgehog project, to land the workspace for whichever core planner selected at Phase 0 — the first real workspace this project gets, since init with no explicit core flag lands the shared agents/skills/build-graph payload and leaves the workspace to bootstrap. Reads the…
doc-onboard
Discovery and understanding of a codebase. Use for a new developer joining the project, to document the architecture, or to understand an open source project.
Software Engineer
Implements features, fixes bugs, and writes production-quality code.
ops-deps
Audit and analysis of dependencies. Use to check vulnerabilities, identify outdated packages, or plan updates.
ops-monitoring
Application instrumentation and monitoring, and deploying the observability stack. Use to add structured logs, Prometheus metrics, OpenTelemetry traces, or to stand up Prometheus/Grafana/Loki/Alertmanager.
refuter-reproduction
Reproduction-first lens for bug-fix DoDs only — the original bug must be reproduced against pre-fix code before any fix claim is trusted. Read-only. Invoked only by mnm-verify, only when the DoD's Goal is a bug fix.