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-dropWrote 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-drop)<a href="https://agentmods.dev/skills/arrrrny/zuraffa/speckit-gym-drop"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-gym-drop/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-drop"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-gym-drop.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 | $0.00357 |
| Opus 5 | $0.00009 | $0.00179 |
| Sonnet 5 | $0.00004 | $0.00071 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
speckit-gym-drop 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: Drop
Record a drop card from a mis-fire. A mis-fire is not a mistake to punish — it is a
discovery to keep. Drop cards capture what was done, what was expected, and what
happened, persisted to the configured redundant stores (default <project>/drops/
plus the extension's append-only .drop-ledger.md).
Usage
bash .specify/extensions/gym/scripts/bash/gym.sh drop \
--agent <you> --where "GYM ex-1" \
--did "..." --expected "..." --happened "..."
# or PowerShell:
powershell .specify/extensions/gym/scripts/powershell/gym.ps1 drop `
--agent <you> --where "GYM ex-1" `
--did "..." --expected "..." --happened "..."
Arguments
--agent— who dropped (person or agent)--where— where in the GYM (e.g.GYM ex-1 warmup-1)--did— what was done--expected— what was expected--happened— what actually happened
Result
Writes the card to each configured store and prints the recorded paths. Missing fields are flagged but the card is still recorded (FR-010).
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.
- 7d ago Changed · -40 lines · -18 tokens per session 07400e6299ef
- 11d ago First seen · 41 lines · 18 tokens per session scan A d57dadb5c060
speckit-gym-drop is a skill published in the GitHub repository arrrrny/zuraffa (5 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 357 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
flutter
Use when building, structuring, testing or optimizing a Flutter app — feature-first layering, Riverpod 3 or Bloc, typed gorouter, freezed models, a dio data layer, Material 3, jank hunting, widget/golden tests. Targets Flutter 3.44 / Dart 3.12. NOT React Native (that is react-native), NOT Compose Multiplatform (that…
building-flutter-apps
Flutter Riverpod app architecture and Windows installer delivery. Use before changing a Riverpod Flutter app/package or its Windows desktop packaging/update pipeline; skip non-Riverpod stacks and pure-Dart work.
fl-data-layer
Builds the data layer with Freezed DTOs, Retrofit clients, the storage-seam local data manager, and repositories wired through injectable.
fl-route-config
Configures routes with the IRoute / CustomRouter abstractions in core and exposes navigation via a BuildContext coordinator.
fl-bloc-pattern
Implements BLoC state management using CoreBlocBase, an abstract State hierarchy, and a freezed StateData.
fl-bus-event
Handles cross-feature BusEvent communication with EventBusManager in the Flutter base template.