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 daehounan/agency-agents-fork --skill skill-routing-arbitratorgit clone --depth 1 https://github.com/daehounan/agency-agents-forkWrote 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/daehounan/agency-agents-fork/skill-routing-arbitrator)<a href="https://agentmods.dev/skills/daehounan/agency-agents-fork/skill-routing-arbitrator"><img src="https://agentmods.dev/badge/skills/daehounan/agency-agents-fork/skill-routing-arbitrator/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/daehounan/agency-agents-fork/skill-routing-arbitrator"><img src="https://agentmods.dev/badge/skills/daehounan/agency-agents-fork/skill-routing-arbitrator.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 | $0.00124 | $0.01852 |
| Opus 5 | $0.00062 | $0.00926 |
| Sonnet 5 | $0.00025 | $0.00370 |
| Haiku 4.5 | $0.00012 | $0.00185 |
Grade A, and why
skill-routing-arbitrator 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Routing Arbitrator
When multiple skills could fire on the same prompt, this skill provides deterministic preferences so Claude routes to the right one.
Priority hierarchy (general)
- Most specific language/domain wins over generic — e.g.,
ecc:python-reviewoverecc:code-review - Active executor wins over strategy/workflow doc — e.g.,
ecc:code-review(runs review) overengineering:code-review(strategy) - Current version wins over dated snapshot — e.g.,
anthropic-skills:mcp-builderoveranthropic-skills:mcp-builder-20260419 - Real skill wins over legacy shim — e.g.,
ecc:tdd-workflowoverecc:tddshim - Connected-data-source skill wins when data is available — e.g.,
common-room:account-researchif Common Room MCP is connected, elsesales:account-research
Specific cluster rules
Code review
| Situation | Skill |
|---|---|
| Language known + active review needed | ecc:<lang>-review (cpp, python, go, rust, kotlin, flutter) |
| PR / multi-agent comprehensive | ecc:review-pr |
| Local diff review | ecc:code-review |
| PR triage (lightweight built-in) | review |
| Security focus on PR | security-review |
| Codebase security review | ecc:security-review |
| Strategy / process discussion only | engineering:code-review |
Testing
| Situation | Skill |
|---|---|
| TDD in language X | ecc:<lang>-test |
| E2E specifically | ecc:e2e-testing |
| Generate tests from existing file | ruflo-testgen:testgen |
| Identify coverage gaps | ruflo-testgen:test-gaps |
| Strategy / test plan | engineering:testing-strategy |
Build error resolution
Pick by language: ecc:cpp-build / go-build / kotlin-build / rust-build / flutter-build / gradle-build.
Security audit
| Situation | Skill |
|---|---|
| Codebase review (vulnerabilities in code) | ecc:security-review |
| Dependency / supply chain CVE | ruflo-security-audit:dependency-check |
| Formal SOC 2 / ISO 27001 / HIPAA readiness | anthropic-skills:security-audit-engine |
| Smart contract / DeFi | agency-agents-fork:compliance-audit-routing → blockchain-security-auditor |
| Healthcare PHI in code | ecc:healthcare-phi-compliance |
| LLM trading agent security | ecc:llm-trading-agent-security |
| Bug bounty mode | ecc:security-bounty-hunter |
| PR-context lightweight | security-review |
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 · 160 lines · 124 tokens per session scan A 32fc9c3b8124
skill-routing-arbitrator is a skill published in the GitHub repository daehounan/agency-agents-fork (2 stars, last pushed 3mo ago), licensed MIT. It adds 124 tokens to every session and 1,852 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
sns
AWS SNS notification service for pub/sub messaging. Use when creating topics, managing subscriptions, configuring message filtering, sending notifications, or setting up mobile push.
cognito
AWS Cognito user authentication and authorization service. Use when setting up user pools, configuring identity pools, implementing OAuth flows, managing user attributes, or integrating with social identity providers.
i18n-parity
MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, mirrored READMEs, locale-aware formatting, language switchers) in parity across every supported language. Use automatically (without being asked) whenever you add or change…
iam
AWS Identity and Access Management for users, roles, policies, and permissions. Use when creating IAM policies, configuring cross-account access, setting up service roles, troubleshooting permission errors, or managing access control.
dag-map
Render the multi-agent orchestration DAG for a session — parent→child subagent edges, tree depth, and fan-out — from the Agent Monitor workflow intelligence API. Cross-checks the orchestration dataset against the raw agent records and session detail. Use when visualizing how a session's agent structure was organized.
update-project-docs
MANDATORY for every coding agent (Claude Code, Codex, or any other) — keep this repository's documentation in sync after any change to behavior, configuration, interfaces, events, schema, or features. Use automatically (without being asked) at the end of ANY change-set that adds or alters an env var, event type, hook…