dojo

A workflow for creating, editing, testing, evaluating, and packaging Claude Code skills, which are instruction packages that change how the coding agent behaves.

In plain words
What is it for?
Writing new skills, editing their instructions, tuning triggers, running focused tests, evaluating behavior, and packaging the result.
Why use it?
It checks whether a skill actually triggers and changes agent behavior before release, rather than treating untested instructions as finished work.

Skill for Claude CodeCodex

Part of the limitless plugin — 10 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/pyros-projects/limitless/dojo
Any agent
npx skills add pyros-projects/limitless --skill dojo
Clone the repo
git clone --depth 1 https://github.com/pyros-projects/limitless

Made for: Claude Code, Codex.

Or install limitless, the plugin that ships this one along with the rest of its 10 skills.

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,697 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00102 $0.01697
Opus 5 $0.00051 $0.00848
Sonnet 5 $0.00020 $0.00339
Haiku 4.5 $0.00010 $0.00170

Measured 3d ago against content hash b4be33385186, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dojo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/limitless/skills/dojo/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dojo — Skills Earn Their Place

Overview

A skill is a claim about future agent behavior. Untested claims ship as liabilities: self-generated, unverified skills measurably make agents worse (SkillsBench −1.3pp), while the same authorship under scored rollouts and validation gates lifts frozen-model accuracy by ~20pp (SkillOpt). It was never agents-writing-skills that failed — it was writing without verification. The dojo is where the verification happens: no skill ships on vibes.

Dojo covers the full lifecycle: create, edit, test, evaluate, package. For small edits, run only the kata that the change touches (a description tweak needs kata 6–7, not a full baseline) — say which kata you're skipping and why.

The Measurability Rule

Automated optimization needs a scalar grader; most skill output quality has none. So dojo never pretend-measures quality. Pass criteria are:

  • Observable process checks — y/n facts about what the agent did ("scoped search to a discovered venue before deep-reading: y/n")
  • Exact-match trigger tests — which skill did the router pick

Holistic output quality stays human/agent judgment, applied openly as judgment. If a skill someday has a real scalar grader, point SkillOpt at it instead of the dojo.

Tiers — Match Rigor to Skill Type

Full TDD on a reference doc is theater. Classify at intake:

Tier What it is Example Rigor
Discipline Rules agents rationalize around verification gates, TDD Full RED-GREEN-REFACTOR + adversarial pressure variants
Technique Multi-step orchestration hivemind, suno-pack Baseline-fail test + skilled-walkthrough test
Reference Facts, flags, recipes searxng Correctness review + trigger eval

Every tier gets the trigger eval (kata 6). Only discipline skills get adversarial variants (time pressure, sunk cost, authority pressure).

The Seven Kata

  1. Intake. What skill, which tier, new or edit. Design the test scenarios NOW — one per archetype the skill claims to handle, each with pre-written y/n pass criteria. Persist the battery immediately to ~/.limitless/dojo/<repo-slug>/<skill>/<skill>-scenarios.md — and during kata 2–6, append every subagent prompt VERBATIM as actually sent, plus each run's result line. Dojo artifacts are skill-owned runtime output: keep them under ~/.limitless/dojo/ by default so target repos do not fill with raw training debris. Curated docs/examples may be copied into the repo only when the user asks. Hold 1–2 scenarios back: never used during iteration, run once at the end (kata 5). If a transcript or session sparked the skill, mine it for scenario material. See references/pressure-testing.md for scenario and criteria design.

Read the full file on GitHub · 139 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 139 lines · 102 tokens per session scan A b4be33385186

Subscribe to this mod's changes

dojo is a skill published in the GitHub repository pyros-projects/limitless (9 stars, last pushed 20d ago), licensed MIT. It adds 102 tokens to every session and 1,697 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.