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 The-Artificer-of-Ciphers-LLC/skills-from-the-artificer --skill cost-routinggit clone --depth 1 https://github.com/The-Artificer-of-Ciphers-LLC/skills-from-the-artificerWrote 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/the-artificer-of-ciphers-llc/skills-from-the-artificer/cost-routing)<a href="https://agentmods.dev/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/cost-routing"><img src="https://agentmods.dev/badge/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/cost-routing/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/the-artificer-of-ciphers-llc/skills-from-the-artificer/cost-routing"><img src="https://agentmods.dev/badge/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/cost-routing.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 | $0.00133 | $0.01273 |
| Opus 5.5 | $0.00053 | $0.00509 |
| Sonnet 5.5 | $0.00027 | $0.00255 |
| Haiku 4.5 | $0.00013 | $0.00127 |
Grade B, and why
cost-routing scanned grade B with 1 finding 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 13d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
The companion PreToolUse hook (`hooks/pre-tool-use-cost-check.sh`) warns when Read / Grep / Glob fires in the main context. Register it in `~/.claude/settings.json` (see EXAMPLES.md § Installing the hook). How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost-Tier Routing
The main context runs on opus. Every Read, Grep, Glob, and Edit invoked at this tier bills at opus rates. Most operations don't need opus reasoning — they need a model that can run a command and report a result. This skill is the dispatch gate that stops opus from doing work haiku or sonnet would complete just as correctly for a fraction of the cost.
The three tiers
| Tier | Model | Owns | Example requests |
|---|---|---|---|
| scout | haiku | Read-only lookup, search, location | "Where is Foo defined?", "List files matching *.test.ts", "Count LOC in src/", "Read X and report Y" |
| coder | sonnet | Bounded code changes at known locations | "Add a test for parseDate", "Refactor auth.ts to use the new client", "Rename A → B repo-wide" |
| architect | opus | Ambiguous spec, tradeoff analysis, design | "Should we use Redux or Zustand?", "Draft an ADR for the auth rewrite", "Why is this architecture failing?" |
The dispatch decision (run this first, every turn)
Before reaching for any tool, run this classifier against the incoming request:
- Is the work entirely read / search / location? → scout. Dispatch
haiku-scout. Never call Read / Grep / Glob in the main context. - Is the change scope AND the design already decided? → coder. Dispatch
sonnet-coderwith a precise brief. - Is the user asking "should we", "why", "what are the tradeoffs", "design X"? → architect. Stay in-context (you ARE opus) or dispatch with
model: "opus". - Mixed? → split. Scout first to gather facts, then re-classify the next step. Never bundle scout work into an architect dispatch.
Tool split (CodeGraph first, Memtrace for heavy hits). Use CodeGraph (codegraph_explore / codegraph CLI) for symbol lookup, file reads, callers/callees, and ordinary blast radius. Reserve Memtrace (and cortex) for git history/evolution, recall_decision, cross-repo/API topology, risky blast radius (get_impact), PR review evidence, and dead code/complexity, because Memtrace costs quota. If ~/.claude/state/memtrace-quota.json says blocked with a future until, never call Memtrace; use CodeGraph until that time.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago Changed · +2 lines 6e56b8604871
- 1mo ago First seen · 59 lines · 133 tokens per session scan B 5248991660f5
cost-routing is a skill published in the GitHub repository The-Artificer-of-Ciphers-LLC/skills-from-the-artificer (6 stars, last pushed yesterday), licensed MIT. It adds 133 tokens to every session and 1,273 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
feature-prioritisation
Aplica marcos de priorización (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) para clasificar características e items del backlog. Úsalo cuando se te pida priorizar características, clasificar un backlog, decidir qué construir a continuación, o evaluar compensaciones entre ideas competidoras. Produce una lista de…
outcome-tracker
Record the testable predictions inside a decision, then score them against reality later — so frameworks earn trust from outcomes, not vibes. Use when committing to a prioritisation, forecast, or plan (to log what it predicts), when asked to review what actually happened, or to compute how well-calibrated past RICE…