speckit-gym-run

speckit-gym-run is a skill for Claude Code, Codex from arrrrny/zuraffa. It costs 18 tokens per session (346 once invoked), scanned A, original, MIT.

A training-run command for a GYM curriculum, where warmup repetitions build familiarity and graded exercises check whether the skill works under load.

In plain words
What is it for?
Use it to run warmups and exercises, wait for submitted exercise markers, evaluate the submissions, and set the GYM gate to open or closed.
Why use it?
It prevents the final gate from opening when a warmup verification or graded exercise fails, while recording whether the full run passed or failed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash .specify/extensions/gym/scripts/bash/gym.sh run.

Good fit Use it to run warmups and exercises, wait for submitted exercise markers, evaluate the submissions, and set the GYM gate to open or closed.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/arrrrny/zuraffa
agentmods
npx agentmods add skills/arrrrny/zuraffa/speckit-gym-run

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for speckit-gym-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-gym-run/github.svg)](https://agentmods.dev/skills/arrrrny/zuraffa/speckit-gym-run)
Your own site
<a href="https://agentmods.dev/skills/arrrrny/zuraffa/speckit-gym-run"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-gym-run/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for speckit-gym-run

Your own site · 80×15
<a href="https://agentmods.dev/skills/arrrrny/zuraffa/speckit-gym-run"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-gym-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 346 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00018 $0.00346
Opus 5 $0.00009 $0.00173
Sonnet 5 $0.00004 $0.00069
Haiku 4.5 $0.00002 $0.00035

Measured 6d ago against content hash 3fb3e6726630, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

speckit-gym-run 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 6d 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.

.agents/skills/speckit-gym-run/SKILL.md · 39 lines

What it actually says

GYM: Run

Full training run: warmup reps grow reflexes, graded exercises prove skill under load, and the gate opens only when every rep is grown and every exercise is passed.

Usage

bash .specify/extensions/gym/scripts/bash/gym.sh run
# or PowerShell:
powershell .specify/extensions/gym/scripts/powershell/gym.ps1 run

Environment overrides:

  • GYM_EXERCISES=skip — warmup only (alias for speckit.gym.warmup)
  • GYM_TIMEOUT=N — cap the exercise wait at N seconds

What it does

  1. Loads reps from the warmup location and runs each verify (warmup). A failed rep blocks the exercises and keeps the gate closed (FR-005).
  2. Loads exercises from the exercises location and, for each, waits for a .submitted marker in the sandbox, then runs evaluate.
  3. Writes gym/.gate (open/closed) and exits 0 if the gate opens, 1 otherwise.

A thrown verify/evaluate is treated as a failure with the error reported (FR-015). With no curriculum defined, the runner reports empty and treats the gate as open (FR-012).

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. 8d ago Changed · -38 lines · -18 tokens per session 960897d3cd6b
  2. 12d ago First seen · 39 lines · 18 tokens per session scan A 3fb3e6726630

Subscribe to this mod's changes

speckit-gym-run is a skill published in the GitHub repository arrrrny/zuraffa (5 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 346 once invoked, about $0.0001 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.