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 agentmods add skills/tarekkharsa/agentstack/route-by-costnpx skills add Tarekkharsa/agentstack --skill route-by-costgit clone --depth 1 https://github.com/Tarekkharsa/agentstackWrote 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/tarekkharsa/agentstack/route-by-cost)<a href="https://agentmods.dev/skills/tarekkharsa/agentstack/route-by-cost"><img src="https://agentmods.dev/badge/skills/tarekkharsa/agentstack/route-by-cost.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.00453 |
| Opus 5 | $0.00026 | $0.00227 |
| Sonnet 5 | $0.00010 | $0.00091 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
route-by-cost 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 5d 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.
What it actually says
Route by cost
Use when orchestrating work across models (subagents, workflow steps, delegation): decide which model does which job, instead of running everything on the most expensive one.
The heuristic
Match each job to the cheapest model that clears the bar:
| Job | Route to |
|---|---|
| Clear-spec implementation, codemods, migrations, data/log analysis | cheapest capable model (a bulk model / Codex) |
| Repo exploration, readers, fact-checks, wiring/config verification | a small fast model |
| Tricky refactors, user-facing code, UI, copy, API design | a strong model |
| Orchestration, synthesis across agents, final review, hard judgment | your best model, used sparingly |
Principles
- Spend the scarce (best) model on judgment, not labor. Its jobs: decide, synthesize, review, and the genuinely hard or taste-critical work. Everything else delegates down.
- If you can fully specify the task, it doesn't need the best model. Write the spec, hand it to a cheaper one.
- Generate cheap, verify smart. A cheap model produces the diff; a strong model reviews it — reviewing costs a fraction of generating.
- Escalate on quality, not price. If a cheap model's output misses the bar, rerun with a stronger one — don't ship mediocre to save cost. Cost is a tie-breaker, not the goal.
- Anything user-facing (UI, copy, API shape) must meet the taste bar — don't cheap out there.
Subagents & workflows
- Don't let subagents or workflow steps silently inherit the orchestrator's model — pass a model explicitly per job.
- For parallel editing agents, isolate them (separate git worktrees) so their edits don't collide.
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.
- 5d ago First seen · 44 lines · 51 tokens per session scan A c092d1445532
route-by-cost is a skill published in the GitHub repository Tarekkharsa/agentstack (3 stars, last pushed 22d ago), licensed Apache-2.0. It adds 51 tokens to every session and 453 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
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.
release-notes
Edit an existing GitHub release's body into the project's bilingual (English + Chinese) template format with a References section built from merged PRs. Use when 修改 release、整理发布说明、release notes、编辑 release 内容、发版后整理、edit release body.
release-notes
Create release notes for a new version tag. Gathers all commits, PRs, issues fixed, and breaking changes since a previous release. Creates the release notes markdown file, tags the repo, and pushes. Asks the user to confirm the base version to diff against.
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.
pr-review
Review a GitHub pull request using multiple expert personas. Takes a PR URL as input, analyzes the changes, and generates comprehensive review feedback from different perspectives (Merge Specialist, Frontend, Backend, Security, DevOps, AI/Agent, SRE, Chief Architect).
generate-agent-card
Generate an A2A agent card JSON by analyzing agent source code in a folder or GitHub URL. Studies the code to detect agent name, skills, tools, auth, protocol, and generates a spec-compliant agent card.