Proof

Proof.

What we've counted, how, and when. Where a result doesn't exist yet, this page says so.

01 · Method

How a number gets on this page.

A number appears here only if it's a count taken from files on disk, or a fact that a test in the repository proves about how a mechanism behaves. Each row below says how it was counted and on what date.

  • CountedSkills, agents, commands and workflows are files counted under each plugin's directory.
  • EstimatedAlways-on weight is the summed length of every skill, agent and command description, because Claude Code keeps those in context all the time, plus the protocol text dojo-protocol injects at the start of each session or fresh context. Tokens are characters divided by four, so they're an estimate. /dojo-doctor:check reports the description part per installed plugin as its always-on weight, and the session-start injection under injection weight, measured from your transcripts. It rounds tokens to the nearest whole number, so its figures can be one higher.
  • EnforcedThe release lint fails any plugin whose always-on descriptions reach 1,000 characters.
02 · Measured

What's counted.

Counts from the plugin directories, and the length of their descriptions, measured on 2026-10-18.
PluginSkillsAgentsCommandsWorkflowsDescription characters
dojo-protocol5400885
dojo-gates1000206
dojo-router1000192
dojo-meter0020169
dojo-verify1000173
dojo-flow1022491
dojo-doctor1010335
dojo-settle3000587
Suite total (8)134523038
Always-on weight: what the suite keeps in context all the time, measured on 2026-10-18.
Always-on sourceCharactersEstimate, tokens
Descriptions of skills, agents and commands, kept in context3038759
dojo-protocol PROTOCOL.md, injected at session start1987496
Always-on total50251255

Method. Skills, agents, commands and workflows are files counted under each plugin's directory. Description characters are the summed length of every skill, agent and command description, after removing quotes; Claude Code keeps those in context all the time. dojo-protocol also injects its PROTOCOL.md at the start of each session or fresh context, so that file's length is its own row. If a project has its own DOJO.md, that is injected instead of it. Each part's token figure is its own characters divided by four, rounded down; it is an estimate, not a tokenizer count. The always-on total adds the parts above it, characters and tokens separately. dojo-suite ships no skills, agents or commands and injects nothing, so it adds no row. Our budget is under 2,000 always-on tokens for the suite and under 1,000 for any other Dojo plugin, and the plugins repository's release check fails above it. That check uses Claude Code's own estimate (claude plugin details), which also counts names and listing overhead, so it reads higher than this table; ALWAYS-ON.md has its current figure for every plugin.

Date. 2026-10-18. Guards in dojo-gates, counted from its guard list: 10.

03 · Open

What hasn't been measured.

  • Not yet measuredWhether a session with the suite costs less than one without it. A with/without eval is how to find out; the scaffolds ship in dojo-settle, and we haven't run them.
  • Not yet measuredWhether it makes Claude Code more accurate.
  • Not yet measuredHow often each guard fires in real use.
  • Not yet measuredHow the mods behave on Claude Code versions other than the one we tested.
04 · Limits

What we won't claim.

No spend figures, no benchmark numbers, no percentage claims. A number will appear here only after a pre-registered with/without run (the method is in dojo-settle) or a count from disk backs it.

The ten rules The suite