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.
git clone --depth 1 https://github.com/tmcfarlane/oh-my-cursorWrote 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/commands/tmcfarlane/oh-my-cursor/cactus-juice)<a href="https://agentmods.dev/commands/tmcfarlane/oh-my-cursor/cactus-juice"><img src="https://agentmods.dev/badge/commands/tmcfarlane/oh-my-cursor/cactus-juice/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/commands/tmcfarlane/oh-my-cursor/cactus-juice"><img src="https://agentmods.dev/badge/commands/tmcfarlane/oh-my-cursor/cactus-juice.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 | $0.00000 | $0.00345 |
| Opus 5.5 | $0.00000 | $0.00138 |
| Sonnet 5.5 | $0.00000 | $0.00069 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
cactus-juice 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 2mo 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
CACTUS JUICE MODE -- "It's the quenchiest!"
Switch to Agent Swarm mode. Trade depth for massive parallelism.
Instructions
-
Decompose the request into 5-10 independent micro-tasks. Each micro-task must be:
- Scoped to a single file or function
- Completable in isolation without depending on other micro-tasks
- Small enough for a worker with minimal context
-
Spawn up to 10 subagents simultaneously, one per micro-task. Use
model: "fast"for all workers. -
Each worker receives ONLY a minimal context packet:
- The specific file path to work on
- The exact change to make
- The constraints below
-
Collect all results and verify cross-file consistency.
-
Fix any integration issues inline rather than re-spawning.
Worker Constraints (include in every worker prompt)
- You have ONE task. Complete it and return.
- Write code with low cognitive complexity:
- Short functions (max 20 lines)
- Minimal nesting (max 2 levels deep)
- No ternary chains
- Early returns over nested ifs
- No clever tricks -- readable beats clever
- Do not explore beyond your assigned file.
- Do not ask questions -- make reasonable assumptions.
- Return: what you changed, what file, and any concerns.
Sequencing Rules
- If a micro-task depends on another, they MUST be sequenced, not parallelized.
- Verify every worker result before considering the task complete.
- If any worker fails, fix the issue inline -- do not re-spawn.
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.
- 2mo ago First seen · 41 lines · 0 tokens per session scan A 01f40825cbfd
cactus-juice is a command published in the GitHub repository tmcfarlane/oh-my-cursor (110 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 345 tokens. 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.
cactus-juice compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cactus-juicetmcfarlane/oh-my-cursor | Command | 110 | 19d ago | MIT | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |