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/promptingbox/mcp/savegit clone --depth 1 https://github.com/promptingbox/mcpWhat 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 | $0.00009 | $0.00232 |
| Opus 5 | $0.00005 | $0.00116 |
| Sonnet 5 | $0.00002 | $0.00046 |
| Haiku 4.5 | $0.00001 | $0.00023 |
Grade A, and why
save 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 yesterday.
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
Save a prompt to the user's PromptingBox account.
Instructions
-
Look at the current conversation context. Identify what the user most likely wants to save:
- If the user just wrote or refined a prompt, save that prompt
- If the conversation contains a system prompt, instruction set, or reusable template, save that
- If unclear, ask the user what they'd like to save
-
Before saving, propose:
- Title: A clear, descriptive title
- Folder: Suggest an appropriate folder based on the prompt's domain (optional)
- Tags: Suggest 1-3 relevant tags (optional)
-
Ask the user to confirm or adjust, then call
save_promptwith the final values. -
After saving, show the user the prompt URL so they can view it in PromptingBox.
If the user provided arguments after the command (e.g., /pbox:save my code review prompt), use that as a hint for what to save.
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.
- yesterday First seen · 26 lines · 9 tokens per session scan A 8c50c8aff961
save is a command published in the GitHub repository promptingbox/mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 232 once invoked, about $0.0000 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 commands, from other repositories
/spdd-reasons-canvas
Generate REASONS-Canvas structured prompts from business context without external template.
optimize-gepa
Run GEPA (Genetic-Pareto) prompt optimization to improve monitor performance.
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
prompt-show
Display full details of a saved prompt by ID.
prompt-test
Test LLM prompts against sample inputs. Shows outputs, checks for regressions when prompts change, and compares different prompt versions side-by-side.
prompt-optimize
Present the efficiency-versus-effectiveness frontier as labelled variants and let the user pick. TRIGGER WHEN: the user wants to review or optimize a prompt, system message, or agent instructions for clarity/tokens/reliability.