Warden Select — Development skill for Claude Code
Measure pending token-warden candidate rules for an agent on the golden suite, evict or activate them, and recompile the agent's memory.
How to install Warden Select
Installs to ~/.claude/skills/vukkt-token-warden-warden-select/SKILL.md
mkdir -p ~/.claude/skills/vukkt-token-warden-warden-select && curl -fsSL https://raw.githubusercontent.com/vukkt/token-warden/HEAD/commands/warden-select.md -o ~/.claude/skills/vukkt-token-warden-warden-select/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Warden Select does
description: Measure pending token-warden candidate rules for an agent on the golden suite, evict or activate them, and recompile the agent's memory. argument-hint: [--runs N] [--top-up N] [--uniform-top-up] [--retention-rounds N] disable-model-invocation: true allowed-tools: Bash(cd:*), Bash(npx tsx:*)
Run the token-warden selector. The agent and any extra flags are: $ARGUMENTS
This spends real benchmark tokens (a shared baseline suite, one suite per can
Alternatives in Development
- Eval Author — Draft a new eval case (eval/cases/ .json) + scaffold its golden folder, golden_pending until captured on the V 136 ★
- Opencode — A powerful, custom opencode configuration, complete with a suite of agents, commands, rules, skills, and a pre 133 ★
- Docmancer — Find out what your coding agents already know 121 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Warden Status
Show token-warden status — per-agent runs and rules, golden-suite totals vs frozen baselines, learning curves,
Warden Bench
Run the golden benchmark suite for one token-warden agent (or all) and compare results against the frozen run1
Memory Curate
Per-entry reduction pass for an over-ceiling reference-topic file (charter/pending/worklog/support/traps/rules
Propose Rules
Review pending memory rule and principle proposals from the digital-twin pushback detector. Approves or reject
Eval Prompts
Run a golden-set prompt eval suite against the pinned baseline; fail on any regression beyond threshold.
Check Todos
List pending todos and select one to work on
Related Agents
Eval Author
Authoring role for the D365FO agent eval loop catalog. Drafts a new eval/cases/ .json spec (valid against eval
Reliability Engineer
Python delivery agent for quality gates and test infrastructure. Owns test suite (>=80% coverage enforced), go
Tax Test Oracle
Builds the independent test suite for a tax engine - sourced golden vectors, property tests, boundary generato