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.
git clone --depth 1 https://github.com/arrrrny/zuraffanpx agentmods add skills/arrrrny/zuraffa/speckit-gym-runWrote 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.
[](https://agentmods.dev/skills/arrrrny/zuraffa/speckit-gym-run)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 forspeckit.gym.warmup)GYM_TIMEOUT=N— cap the exercise wait at N seconds
What it does
- Loads reps from the warmup location and runs each
verify(warmup). A failed rep blocks the exercises and keeps the gate closed (FR-005). - Loads exercises from the exercises location and, for each, waits for a
.submittedmarker in the sandbox, then runsevaluate. - Writes
gym/.gate(open/closed) and exits0if the gate opens,1otherwise.
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).
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.
- 8d ago Changed · -38 lines · -18 tokens per session 960897d3cd6b
- 12d ago First seen · 39 lines · 18 tokens per session scan A 3fb3e6726630
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.
Other skills, from other repositories
gws-classroom
Google Classroom: Manage classes, rosters, and coursework.
get-rep-call-feedback
Use when the user wants evidence-backed coaching for one rep's calls, especially by comparing the rep with peer examples to identify repeatable best practices, specific upgrade moments, and practical next-call language.
recipe-create-classroom-course
Create a Google Classroom course and invite students.
tutorial
Interactive tutorial teaching Ouroboros hands-on.
printing-press-retro
Use when the user asks to retro, run a retrospective, file findings, or improve the Printing Press after a printed-CLI run. Trigger phrases: "retro", "retrospective", "what went wrong", "improve the press", "post-mortem", "lessons learned", "what can we improve", "file a retro", "submit findings". Do not use for…
socratic-quiz
Use this when the user wants to deeply understand something through guided questioning. Trigger phrases include: "quiz me", "help me understand", "Socratic", "teach me", "walk me through with questions", "test my understanding", or when the user asks for an explanation and would benefit more from guided discovery than…