Agent Squad Python Guide
2FastLabs/agent-squad
Map of the agent-squad Python framework for async multi-agent orchestration: which agent, classifier, storage and tool provider to pick, and the pitfalls to avoid.
A skill your agent uses when evaluating BitRouter route decisions or Eval Exchange subjects with task-native verifiers, human reviewers, private enterprise evaluators, agentic judges, or genuinely…
Install Evaluating Bitrouter Routes
$ npx skills add bitrouter/bitrouter --skill evaluating-bitrouter-routes -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install bitrouter/bitrouter evaluating-bitrouter-routes --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/bitrouter/bitrouter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/evaluating-bitrouter-routes .claude/skills/evaluating-bitrouter-routes && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "evaluating-bitrouter-routes" agent skill from https://github.com/bitrouter/bitrouter/tree/main/skills/evaluating-bitrouter-routes into .claude/skills/evaluating-bitrouter-routes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluating-bitrouter-routes", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/bitrouter/bitrouter/tree/main/skills/evaluating-bitrouter-routesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add bitrouter/bitrouter --skill evaluating-bitrouter-routes -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install bitrouter/bitrouter evaluating-bitrouter-routes --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bitrouter/bitrouter.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/evaluating-bitrouter-routes .agents/skills/evaluating-bitrouter-routes && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "evaluating-bitrouter-routes" agent skill from https://github.com/bitrouter/bitrouter/tree/main/skills/evaluating-bitrouter-routes into .agents/skills/evaluating-bitrouter-routes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluating-bitrouter-routes", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bitrouter/bitrouter --skill evaluating-bitrouter-routes -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install bitrouter/bitrouter evaluating-bitrouter-routes --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bitrouter/bitrouter.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/evaluating-bitrouter-routes .cursor/skills/evaluating-bitrouter-routes && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "evaluating-bitrouter-routes" agent skill from https://github.com/bitrouter/bitrouter/tree/main/skills/evaluating-bitrouter-routes into .cursor/skills/evaluating-bitrouter-routes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluating-bitrouter-routes", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/bitrouter/bitrouter.git --path skills/evaluating-bitrouter-routes--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add bitrouter/bitrouter --skill evaluating-bitrouter-routes -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install bitrouter/bitrouter evaluating-bitrouter-routes --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bitrouter/bitrouter.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/evaluating-bitrouter-routes .gemini/skills/evaluating-bitrouter-routes && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "evaluating-bitrouter-routes" agent skill from https://github.com/bitrouter/bitrouter/tree/main/skills/evaluating-bitrouter-routes into .gemini/skills/evaluating-bitrouter-routes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluating-bitrouter-routes", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install bitrouter/bitrouter evaluating-bitrouter-routesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add bitrouter/bitrouter --skill evaluating-bitrouter-routes -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/bitrouter/bitrouter.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/evaluating-bitrouter-routes .github/skills/evaluating-bitrouter-routes && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "evaluating-bitrouter-routes" agent skill from https://github.com/bitrouter/bitrouter/tree/main/skills/evaluating-bitrouter-routes into .github/skills/evaluating-bitrouter-routes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluating-bitrouter-routes", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bitrouter/bitrouter --skill evaluating-bitrouter-routes -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install bitrouter/bitrouter evaluating-bitrouter-routes --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bitrouter/bitrouter.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/evaluating-bitrouter-routes .opencode/skills/evaluating-bitrouter-routes && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "evaluating-bitrouter-routes" agent skill from https://github.com/bitrouter/bitrouter/tree/main/skills/evaluating-bitrouter-routes into .opencode/skills/evaluating-bitrouter-routes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluating-bitrouter-routes", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
evaluating-bitrouter-routes- GitHub stars
- 235
- Token cost
- ~1.2k tokens
- SKILL.md length
- 557 words
- Files
- 3 (incl. references)
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses when evaluating BitRouter route decisions or Eval Exchange subjects with task-native verifiers, human reviewers, private enterprise evaluators, agentic judges, or genuinely…
- Works in 6 steps: Copy every decision's decision_id,… → Redact evidence before it leaves its… → List only dimensions the evaluator was… → …
- Evaluating BitRouter route decisions
- SKILL.md covers Classify the evaluation, Build the evaluator packet, Submit and hand off and Keep the packet consistent
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Evaluating Bitrouter Routes is an agent skill from bitrouter/bitrouter. Use when evaluating BitRouter route decisions or Eval Exchange subjects with task-native verifiers, human reviewers, private enterprise evaluators, agentic judges, or genuinely uncategorized evaluator sources.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/eval-exchange.md`).
It sits in AI & LLM Engineering, covering Model routing and gateways. It works with Model Context Protocol, OpenAI and Rust. The repository describes itself as: The minimal interpretable model router that learns & adapts to your agent workflows. The licence is Apache-2.0.
When your agent uses it
- Evaluating BitRouter route decisions
- Eval Exchange subjects with task-native verifiers
- Human reviewers
- Private enterprise evaluators
Example prompts
- “/evaluating-bitrouter-routes”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Copy every decision's decision_id, policy, route_projection,
- Redact evidence before it leaves its private source. Retain raw messages,
- List only dimensions the evaluator was asked to judge. Leave unsupported
- Set confidence_ppm to the evaluator's confidence that its verdict is
- Write a draft subject with an empty evidence_digest, then seal it
- For a multi-decision subject, derive decision_credit from the fixed
What it can do on your machine
Read from SKILL.md and the folder at commit d6dfc24. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Evaluating Bitrouter Routes loads about 1.2k tokens when it runs, and up to ~4.8k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 557 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from bitrouter/bitrouter at commit d6dfc24, republished under its Apache-2.0 licence (© bitrouter). 557 words, ~1,216 tokens.
Download SKILL.mdSave it as
.claude/skills/evaluating-bitrouter-routes/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- evaluating-bitrouter-routes
- description
- Use when evaluating BitRouter route decisions or Eval Exchange subjects with task-native verifiers, human reviewers, private enterprise evaluators, agentic judges, or genuinely uncategorized evaluator sources.
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:bash bro eval subject seal subject-draft.json --output subject.jsonFor a multi-decision subject, derive
decision_creditfrom the fixed evaluator credit policy:- Exact supported decision/metric mappings: emit only those mappings.
- No policy or no exact mapping: use
{}or omit the serde-defaulted field. The result remains a record but produces no per-route evidence. For a one-decision subject, empty credit means implicit full credit. When an inconclusive evaluator intentionally withholds attribution, emit that decision withweight_ppm: 0instead. Keep hypothetical or illustrative weights outside submit-ready JSON.
Show full SKILL.md (227 more words)Show less
Submit and hand off
Insert the sealed subject and submit a result that repeats its exact
eval_idandevidence_digest.bash bro eval subject put subject.json --config bitrouter.yaml bro eval result submit result.json --config bitrouter.yamlTreat an
admittedresponse as eligible evidence. Preserveheld_out,rejected, anddisputedresponses as non-training records.Hand off the sealed subject, result, submission response, and private evidence references, then stop. A later
bro optimize runinvocation is a separate autonomous authorization; do not review, publish, or run it as part of evaluation.
Keep the packet consistent
- Use
subject sealfor canonical evidence hashing and JSON. - Attribute metrics only to evidence-supported decisions.
- Never copy a task- or episode-level reward onto each request. Use a fixed causal policy (for example, a matched control plus one changed route family) or withhold credit.
- Preserve the router-authored baseline and selected tiers.
- Preserve router-authored experiment references exactly.
Optimizer membership never comes from the evaluator-owned
cohortstring. - Treat
inconclusiveas zero quality evidence even if an old or malformed packet assigns positive quality credit. Attribute cost or latency separately. - Keep evaluator identity, rubric/config digest, evidence references, confidence, and idempotency key stable for an equivalent retry.
- Keep
eval_id, result, and evidence identities attempt-specific. For task scope, keepsubject_idstable for the canonical task inside its explicit run/source/policy namespace so repeated attempts cannot inflate the generic compiler's independent-task count.
© bitrouter, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in skills/evaluating-bitrouter-routes of bitrouter/bitrouter.
- SKILL.md
- agents/openai.yaml
- references/eval-exchange.md
Open the folder on GitHubat commit d6dfc24
Compare with similar skills
Evaluating Bitrouter Routes next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Evaluating Bitrouter Routes this skillbitrouter/bitrouter | 235 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Agent Squad Python Guide2FastLabs/agent-squad | 7.8k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | |
| Using Ccproxy Inspectorstarbaser/ccproxy | 350 | — | ~2.7k | Automated safety check: Pass | Custom licence | |
| Caching Architecturemajiayu000/litellm-rs | 117 | — | ~2k | Automated safety check: Pass | MIT | |
| Config Architecturemajiayu000/litellm-rs | 117 | — | ~3.2k | Automated safety check: Pass | MIT | |
| Cognee Integrations Setuptopoteretes/cognee | 32k | — | ~1k | Automated safety check: Notes | Apache-2.0 |
Similar skills
Using Ccproxy Inspector
starbaser/ccproxy
Operates the ccproxy inspector MITM system for intercepting, inspecting, and transforming LLM API traffic.
Caching Architecture
majiayu000/litellm-rs
LiteLLM-RS response caching architecture. An agent skill from majiayu000/litellm-rs.
Config Architecture
majiayu000/litellm-rs
LiteLLM-RS Configuration Architecture. An agent skill from majiayu000/litellm-rs.
Cognee Integrations Setup
topoteretes/cognee
Switches cognee's LLM, embedding, relational, vector and graph backends through environment variables, with the extras to install and the traps to avoid.
Streaming Architecture
majiayu000/litellm-rs
LiteLLM-RS Streaming Architecture. An agent skill from majiayu000/litellm-rs.
More from bitrouter/bitrouter
Run Bitrouter Benchmark
bitrouter/bitrouter
A skill your agent uses when a user wants to run, compare, resume, audit, share, or submit a Harbor benchmark through BitRouter, including choosing a Harbor dataset and agent, confirming routed…
Related
Works with
Categories
Questions about Evaluating Bitrouter Routes
What does Evaluating Bitrouter Routes do?
A skill your agent uses when evaluating BitRouter route decisions or Eval Exchange subjects with task-native verifiers, human reviewers, private enterprise evaluators, agentic judges, or genuinely…. Evaluating Bitrouter Routes is an agent skill from bitrouter/bitrouter. Use when evaluating BitRouter route decisions or Eval Exchange subjects with task-native verifiers, human reviewers, private enterprise evaluators, agentic judges, or genuinely uncategorized evaluator sources.
When should I use Evaluating Bitrouter Routes?
Evaluating Bitrouter Routes fits situations like: evaluating BitRouter route decisions; eval Exchange subjects with task-native verifiers; human reviewers; private enterprise evaluators.
How do I install Evaluating Bitrouter Routes in Claude Code?
Run `npx skills add bitrouter/bitrouter --skill evaluating-bitrouter-routes -a claude-code`. Or copy the skill folder (skills/evaluating-bitrouter-routes in bitrouter/bitrouter) into .claude/skills/evaluating-bitrouter-routes in your project. Claude Code loads it when a task matches its description.
How do I install Evaluating Bitrouter Routes in Codex?
Run `npx skills add bitrouter/bitrouter --skill evaluating-bitrouter-routes -a codex`. Or copy the skill folder (skills/evaluating-bitrouter-routes in bitrouter/bitrouter) into .agents/skills/evaluating-bitrouter-routes in your project. Codex loads it when a task matches its description.
Can I use Evaluating Bitrouter Routes in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bitrouter/bitrouter --skill evaluating-bitrouter-routes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evaluating-bitrouter-routes, .gemini/skills/evaluating-bitrouter-routes, .github/skills/evaluating-bitrouter-routes and .opencode/skills/evaluating-bitrouter-routes in your project.
What does Evaluating Bitrouter Routes need to run?
SKILL.md names no scripts, command-line tools or credentials: Evaluating Bitrouter Routes is instructions for the agent only.
Does Evaluating Bitrouter Routes access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Evaluating Bitrouter Routes safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Evaluating Bitrouter Routes use?
Evaluating Bitrouter Routes is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Evaluating Bitrouter Routes use?
About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.6k tokens, read only when the agent opens those files.
What are the alternatives to Evaluating Bitrouter Routes?
Skills that share tags, products or a category with Evaluating Bitrouter Routes: Agent Squad Python Guide (2FastLabs/agent-squad, 7.8k stars), Using Ccproxy Inspector (starbaser/ccproxy, 350 stars), Caching Architecture (majiayu000/litellm-rs, 117 stars) and Config Architecture (majiayu000/litellm-rs, 117 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Evaluating Bitrouter Routes?
bitrouter (a GitHub organization) maintains it in bitrouter/bitrouter, which has 235 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 8, 2026.
Source: bitrouter/bitrouter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.