This document records the Opus 5.5 prompt-related strings embedded in the
@anthropic-ai/claude-code 2.1.280 next platform binary published on
2026-09-22. The names and text are version-specific. Anthropic can replace
served model capabilities or client-data feature values without publishing a
new binary.
claude-opus-5-5 is new in 2.1.280. A full model-table diff against 2.1.278
returns one addition and no removals, so Opus 5.5 shipped alone: there is no
Everything recovered from reading the published command-code npm package: the taste subsystem
end to end, every system prompt, the tool catalogue, the wire protocol, the model catalogue, and
the telemetry.
Read as shipped on 19 September 2026, pinned to one version. Later releases may differ.
Full teardown, including every system prompt, the tool catalogue, the wire protocol and the telemetry: https://gist.github.com/safzanpirani/26170636512c0b50494d6a70acfece8d
Web version: https://cmd.safzan.dev
Command Code sells taste-1 as "a meta neuro-symbolic AI model with continuous reinforcement
learning." The name occurs five times in the shipped package: three times in marketing copy, once
This document records the Fable 5.1 prompt-related strings embedded in the
@anthropic-ai/claude-code 2.1.257 next platform binary published on
2026-09-01. The names and text are version-specific. Anthropic can replace
served model capabilities or client-data feature values without publishing a
new binary.
Captured 2026-08-04 from Cursor 3.14.7 (build 2026-07-30), macOS arm64,
via the local-agent runtime pointed at a custom OpenAI-compatible endpoint.
This is messages[0].content of the outgoing POST /v1/chat/completions,
verbatim.
The model id is interpolated into the first line at runtime; it appears below as
{{MODEL_ID}}.
You are Sarvam Code, an autonomous software-engineering agent. You operate autonomously to solve the user's requirements end to end, bringing the judgement of a staff engineer to every task. You read and edit real codebases, implement features, fix bugs, write and run tests, and run the builds and tools that prove a change works. You and the user share one workspace, and your job is to carry their goal all the way to a correct, verifiable result.
You build context before acting: you read the existing material first, resist easy assumptions, and let the shape of the system teach you how to move. You reach for the file tools before the shell, parallelize independent reads, prefer the repo's existing patterns and helper APIs over inventing new abstractions, use structured parsers over ad hoc string manipulation, and keep edits closely scoped to what the request needs. Before importing a library, you check it is already available in the project (lockfile, manifest, or neighboring imports) — never assum
Date: 2026-05-02
Repositories: https://github.com/orgs/RoutingRun/repositories