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 bitrouter/bitrouter --skill evaluating-bitrouter-routesgit clone --depth 1 https://github.com/bitrouter/bitrouterWrote 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/bitrouter/bitrouter/evaluating-bitrouter-routes)<a href="https://agentmods.dev/skills/bitrouter/bitrouter/evaluating-bitrouter-routes"><img src="https://agentmods.dev/badge/skills/bitrouter/bitrouter/evaluating-bitrouter-routes.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.01049 |
| Opus 5 | $0.00022 | $0.00524 |
| Sonnet 5 | $0.00009 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
evaluating-bitrouter-routes 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 3d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluate BitRouter Routes
Evaluate outcomes outside BitRouter's serving path. Produce an immutable result and stop after BitRouter reports its admission status. Do not run the optimizer or use low-level policy publication from the evaluator workflow.
Read the Eval Exchange reference before forming a subject or result. It is the exact current wire and authority contract.
Classify the evaluation
Choose scope from the observable outcome boundary:
| Evidence boundary | Scope |
|---|---|
| One request-local outcome | request |
| Bounded multi-request workflow or conversation | episode |
| Externally defined task identity plus terminal task or verifier outcome | task |
Choose evaluator.kind from the actual source:
| Evaluation source | Kind |
|---|---|
| Task-native verifier | task_native |
| Human reviewer | human |
| Private enterprise evaluator | enterprise |
| Agentic judge | agentic |
| Genuinely uncategorized evaluator | generic |
Build the evaluator packet
- Copy every decision's
decision_id,policy,route_projection,request_key,selected_tier,baseline_tier,policy_digest, and optionalexperimentobject from router-authored evidence. Preserve the experiment object verbatim; never invent or edit its id, arm, assignment unit, assignment-id digest, or challenger propensity. - Redact evidence before it leaves its private source. Retain raw messages, tool arguments, code, and evaluator output with the evaluator; place safe, content-addressed evidence items in the subject.
- List only dimensions the evaluator was asked to judge. Leave unsupported
dimensions absent. Use
inconclusivewhen evidence cannot support a verdict. - Set
confidence_ppmto the evaluator's confidence that its verdict is correct. Usenullwhen the evaluator or rubric does not supply confidence. For a task or episode cost result, submit the complete unit cost ascost.usd_microswith unitmicro_usd; never substitute one request's price for the complete task or episode. - Write a draft subject with an empty
evidence_digest, then seal it:
What ships with it
2 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.
- 3d ago Changed · +9 lines 3c0b8e5f9aae
- 8d ago First seen · 95 lines · 44 tokens per session scan A 42e4470cce79
evaluating-bitrouter-routes is a skill published in the GitHub repository bitrouter/bitrouter (224 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 1,049 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
oma-debug
Bug diagnosis and fixing specialist - analyzes errors, identifies root causes, provides fixes, and writes regression tests. Use for bug, debug, error, crash, traceback, exception, and regression work.
oma-qa
Quality assurance specialist for security, performance, accessibility, comprehensive testing, and quality standard alignment. Use for test, review, security audit, OWASP, coverage, lint work, and ISO/IEC 25010 or ISO/IEC 29119-aligned QA recommendations.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.