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.
npx agentmods add commands/botchetdig/workout-gate/workoutgit clone --depth 1 https://github.com/BotchetDig/workout-gateWhat 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 | $0.00013 | $0.00548 |
| Opus 5 | $0.00006 | $0.00274 |
| Sonnet 5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
workout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
The user manages the Workout Gate (exercise challenge before prompts). Their request: "$ARGUMENTS"
Run the matching command with Bash, from the project root, exactly in this form, and relay the output concisely:
- no arguments → run
.venv/bin/python -m workout_gate statusand show a compact summary; remind the user that! workoutpops the zero-token arrow-key dashboard in a Terminal window. on/off→.venv/bin/python -m workout_gate on(oroff)now→.venv/bin/python -m workout_gate now— run it WITHOUT sandboxing (webcam access needed) and with a 300000ms timeoutstop→.venv/bin/python -m workout_gate stop(closes a running challenge window)stats/status→.venv/bin/python -m workout_gate stats/... statussetup→ tell the user to run! workout setupthemselves (interactive wizard, needs a terminal)ui→ tell the user to type! workout(it pops the dashboard in a Terminal window; you cannot host it yourself)debug on|off→.venv/bin/python -m workout_gate debug <action>(overlay skeleton + live angle)global on|off|status→.venv/bin/python -m workout_gate global <action>(install/remove for ALL Claude Code sessions)enable|disable <exercise>→.venv/bin/python -m workout_gate enable <exercise>(or disable)preset chill|demo|hardcore→.venv/bin/python -m workout_gate preset <name>freq N→.venv/bin/python -m workout_gate set freq Nreps [EXERCISE] MIN MAX→.venv/bin/python -m workout_gate set reps EXERCISE MIN MAX(exercise optional, defaults to pushups)time N/chance P→.venv/bin/python -m workout_gate set time N/... set chance Pmode choice|random→.venv/bin/python -m workout_gate set mode <value>
If now fails with a webcam/permission error, tell the user to run it themselves with: ! workout now (macOS may need camera permission granted to the terminal first).
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.
- 2d ago First seen · 27 lines · 13 tokens per session scan A 056f5745c532
workout is a command published in the GitHub repository BotchetDig/workout-gate (220 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 548 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.