{"actions":{"bootstrapAndRun":{"effect":"installs rote if missing, inspects, prepares, and asks before running","href":"https://play.modiqo.ai/install?play=himanshu-jha/agent-context-tax@0.1.0","method":"GET","rel":"https://rote.dev/rels/bootstrap-and-run","requiresConsent":true,"responseMediaType":"text/x-shellscript"},"inspect":{"command":"rote play inspect https://play.modiqo.ai/himanshu-jha/agent-context-tax@0.1.0","effect":"read-only"},"installCliOnly":{"effect":"installs the rote CLI, nothing else","href":"https://play.modiqo.ai/install","method":"GET","rel":"https://rote.dev/rels/install-cli","requiresConsent":true,"responseMediaType":"text/x-shellscript"},"run":{"command":"rote play run https://play.modiqo.ai/himanshu-jha/agent-context-tax@0.1.0","effect":"executes the play locally after consent","headless":{"approvalAssertion":"--yes","approvalRequiredBeforeInvocation":true,"commandTemplate":"rote play run https://play.modiqo.ai/himanshu-jha/agent-context-tax@0.1.0 <name=value...> --yes","stdinPolicy":"never pipe input to automate the interactive Ready selector"},"requiresConsent":true}},"description":"Tells you how much of the model's context window your installed agent tooling spends before you type anything. Every configured MCP server puts its tool schemas in front of the model at the start of every session, and every installed skill puts its name and description there so the model can decide whether to load it. None of that is visible and none of it is free: the bill arrives as a window that is already part full. Run on the machine that wrote this, it found 36,765 estimated tokens, 18.4 percent of a 200,000 token window, spent on 123 tool schemas and 90 skills before the first word of the task. It measures rather than infers: each stdio server is started, an initialize handshake is completed, tools/list is called, and the real reply is what gets counted, because a config block is not evidence a server answers or evidence of what it costs. Five stages run as a DAG: a declaration survey that answers even when a later handshake hangs, the server measurement, the skill and subagent survey, a cross-server r","distribution":{"digest":"sha256:baeab1e3a2a367b77954390cb2e15a8e69f91b6cdca0f264a6a7356ef0c4f6ed","mediaType":"application/vnd.modiqo.rote-flow","size":19333,"verifiedBy":"rote verifies the downloaded archive against this digest before it runs"},"effects":{"credentialsProvidedBy":"runner","credentialsRemainLocal":true,"declaredWrites":[],"publisherReceivesCredentials":false},"id":"https://play.modiqo.ai/himanshu-jha/agent-context-tax@0.1.0","inputPolicy":{"optionalWithDefault":"show_default_and_accept_override","optionalWithoutDefault":"omit_unless_supplied","required":"ask","secrets":"collect_locally_outside_conversation"},"license":"MIT","links":{"docs":"https://rote.dev","page":"https://play.modiqo.ai/himanshu-jha/agent-context-tax@0.1.0","protocol":"https://play.modiqo.ai/.well-known/rote","self":"https://play.modiqo.ai/himanshu-jha/agent-context-tax@0.1.0.json"},"name":"agent-context-tax","owner":{"kind":"org","slug":"himanshu-jha"},"parameters":[{"default":"200000","description":"The context window the percentage is quoted against, in tokens. It is a stated assumption printed in the report, not a fact this play reads from your model.","example":"200000","input":{"allowCustom":true,"choices":[],"label":"Window"},"name":"window","required":false,"type":"string"},{"default":"20","description":"Seconds to wait for each server to answer initialize and tools/list. A cold npx start is genuinely slow, so a low value here reports working servers as unmeasured.","example":"20","input":{"allowCustom":true,"choices":[],"label":"Timeout"},"name":"timeout","required":false,"type":"string"},{"default":"40","description":"Most servers to start. Anything beyond this is reported as not reached rather than silently dropped, and makes the total an explicit lower bound.","example":"40","input":{"allowCustom":true,"choices":[],"label":"Limit"},"name":"limit","required":false,"type":"string"}],"preparation":[{"action":{"command":"rote play inspect https://play.modiqo.ai/himanshu-jha/agent-context-tax@0.1.0 --json","effect":"read-only"},"step":1,"type":"inspect_local_readiness"},{"references":["/parameters"],"step":2,"type":"collect_parameters"},{"references":["/parameters","/requirements","/effects"],"step":3,"type":"review"},{"consentBoundary":"the user approves the exact play and parameter values","references":["/parameters","/requirements","/effects"],"step":4,"type":"obtain_run_consent"},{"action":{"command":"rote play run https://play.modiqo.ai/himanshu-jha/agent-context-tax@0.1.0","headlessCommandTemplate":"rote play run https://play.modiqo.ai/himanshu-jha/agent-context-tax@0.1.0 <name=value...> --yes"},"preservesAcquisitionBoundaries":["adapter_selection","oauth_dcr","google_discovery","static_token_setup","runtime_security_checks"],"requiresConsent":true,"step":5,"type":"run"}],"producedBy":{"roteVersion":"0.78.0"},"publishedAt":"2026-09-04T14:01:58.245203+00:00","reference":"himanshu-jha/agent-context-tax@0.1.0","requirements":{"adapters":[],"browser":{"dependencies":[],"runtime":false,"signIn":false},"localTools":["python3"],"roteCli":{"minimumVersion":"0.62.0"},"sessions":false},"resolution":"pinned","schema":"rote.play.v1","stats":{"downloads":2,"installs":0},"steps":{"count":5,"names":["budget","heaviest","servers","skills","survey"]},"title":"agent-context-tax","type":"play","version":"0.1.0","visibility":"public"}