Borrowing it
Nothing to install: this file belongs to fqmyysjjd/agent-feed. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fqmyysjjd/agent-feed/main/.agents/skills/specialist-router/SKILL.mdgit clone --depth 1 https://github.com/fqmyysjjd/agent-feedWrote 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/fqmyysjjd/agent-feed/specialist-router)<a href="https://agentmods.dev/skills/fqmyysjjd/agent-feed/specialist-router"><img src="https://agentmods.dev/badge/skills/fqmyysjjd/agent-feed/specialist-router/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/fqmyysjjd/agent-feed/specialist-router"><img src="https://agentmods.dev/badge/skills/fqmyysjjd/agent-feed/specialist-router.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 | $0.00055 | $0.00810 |
| Opus 5 | $0.00028 | $0.00405 |
| Sonnet 5 | $0.00011 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
specialist-router 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specialist Router
Use this skill to route work to optional, imported, custom, or highly specialized skills without letting those skills override the Agent Feed workflow.
Required Use
Use this skill when:
- A task, diff, failed check, review finding, or user request appears to match a specialized skill.
- Multiple skills could apply and the AI needs to choose the smallest useful method.
- A custom or externally imported skill may be useful for the current result.
- A review or fix would benefit from a language, framework, architecture, security, release, document, or domain-specific method.
- The user asks how an imported skill enters the normal Agent Feed workflow.
Required Reading
.agents/rules/outcome-boundary.md.agents/rules/context-loading.md.agents/rules/change-risk-gates.md.agents/skills/README.md.agents/project/README.mdwhen project-specific constraints may affect the routing..agents/domain/README.mdwhen domain contracts or concepts may affect the routing.- The top candidate
SKILL.mdfiles only after candidates are narrowed from the index.
Routing Workflow
- Recover the Task Brief and current stop condition.
- Read
.agents/skills/README.mdas the skill index. - Match candidate skills by task intent, changed surface, failure type, risk category, file type, domain trigger, and user wording.
- Exclude skills that do not serve the current Task Brief or that conflict with
AGENTS.md,.agents/rules/,.agents/project/,.agents/domain/, or the current user request. - Choose at most three candidate skills. Prefer the smallest method that directly helps the current result.
- Classify each candidate's
sourceandtrust. - For
trust: customor external skills, inspect the skill before following it. Treat it as advisory method guidance only. - If a skill suggests commands, network access, destructive changes, credential handling, persistence changes, dependency changes, or writes outside the Task Brief, apply
.agents/rules/change-risk-gates.mdbefore acting. - Ask for confirmation when using the skill would change scope, write set, public behavior, risk class, or future development results.
- Use the selected skill as a method, then return to the normal Agent Feed gates for verification, review, and handoff.
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 · 64 lines · 55 tokens per session scan A 1dcc33c25659
specialist-router is a skill published in the GitHub repository fqmyysjjd/agent-feed (4 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 810 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
claude-code-session-broker
Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.
arcgentic
Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.
verify-gates
Runs the mechanical quality gates that the arcgentic state machine requires for state transitions. Invoked indirectly by transition.sh OR directly by orchestrator agent before declaring a state transition. Use when about to call transition.sh OR when manually verifying that a round artifact meets the gate criteria.…
session-mode
Use when a project has not yet stored session mode, when a user asks for complete arcgentic workflow execution, or when role identity handoff prompts are needed.
agency-roster
Use when a round references agency-agents catalogs, role-family routing, multi-agent identity prompts, or English/Chinese specialist role catalogs.
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.