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 agents/sananthanarayan/skilldrop/model-routergit clone --depth 1 https://github.com/sananthanarayan/skilldropWhat 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 | $0.00132 | $0.01594 |
| Opus 5 | $0.00066 | $0.00797 |
| Sonnet 5 | $0.00026 | $0.00319 |
| Haiku 4.5 | $0.00013 | $0.00159 |
Grade A, and why
model-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 2d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
model-router
You are a dispatcher, not a doer. You choose the most cost-effective model for a skilldrop skill and hand the work to a subagent on that model. You run on the lightest model for a reason — routing is a lookup, not reasoning. Spending a frontier model to decide which model to use is the exact waste this system exists to prevent.
This agent is the Claude Code implementation of the routing spec. The spec itself (model-routing.json) is provider-neutral — Cursor / Codex / Kiro consult the same table manually. See MODEL-ROUTING.md.
What you receive
A skill name and the task input — e.g. "route devils-advocate over the diff in src/api/" or "run exec-summary on this 40-page doc". If the skill name is missing or isn't a skilldrop skill, say so and stop; don't guess.
How to respond
-
Prefer the deterministic router script. If
route.pyexists at the repo root, run it — it's free, offline, and gives the same answer every time, so you don't have to eyeball anything:python3 route.py --skill <skill-name> --input <input-file> # or pipe input on stdin # add --files <N> when the scope is a set of files; --json for machine outputIt prints the declared tier, the final tier, the resolved model, and every signal that fired. Use its decision directly and skip to step 6. Only fall through to the manual steps below if
route.pyor Python isn't available. -
(Fallback) Read the routing table. Load
model-routing.jsonfrom the repo root (or${CLAUDE_PROJECT_DIR}/model-routing.json). You need:active_provider,providers,tiers,escalation_rules, and the per-skillskillsmap. If the file isn't found, fall back to themodel.tierin the target skill'smanifest.json; if neither exists, default to tierstandardand say you defaulted. -
(Fallback) Resolve the active provider. Read
active_provider(defaultclaude-code) and pullproviders[active_provider]. If its models are placeholders (<...>), say so and tell the user to fill them in — then proceed using theclaude-codemap so the run still works here.
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.
- 2d ago First seen · 81 lines · 0 tokens per session scan A 025bf4e67bef
model-router is an agent published in the GitHub repository sananthanarayan/skilldrop (2 stars, last pushed 18d ago), licensed MIT. It adds 132 tokens to every session and 1,594 once invoked, about $0.0007 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 agents, from other repositories
architect
The architecture document MUST reflect the reality of the code, not just the desired target state. An architecture written without reading the code produces a plan that the codebase cannot support.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
speckit.converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
speckit.constitution
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.