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/joseph0926/prompt-shield/helpgit clone --depth 1 https://github.com/joseph0926/prompt-shieldWrote 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/joseph0926/prompt-shield/help)<a href="https://agentmods.dev/commands/joseph0926/prompt-shield/help"><img src="https://agentmods.dev/badge/commands/joseph0926/prompt-shield/help.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.02190 |
| Opus 5 | $0.00005 | $0.01095 |
| Sonnet 5 | $0.00002 | $0.00438 |
| Haiku 4.5 | $0.00001 | $0.00219 |
Grade B, and why
help scanned grade B with 1 finding 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 3d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
description: Show prompt-shield usage guide and command reference How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PromptShield - Help
Input: $ARGUMENTS
⚠️ MANDATORY EXECUTION RULE
This command MUST be executed when user types
/ps:helpThe Claude agent MUST:
- Invoke this skill via the Skill tool IMMEDIATELY
- NEVER simulate or mimic this skill's output without proper invocation
- NEVER skip showing the help content
Available Topics
Parse the input argument to determine which help topic to show:
commandsorcmd- List all slash commandslint- LINT mode detailed guidebuild- BUILD mode detailed guiderevieworr- Review mode guideinterceptora- Intercept/Auto mode guide8point,7point, orquality- 8-Point Quality Check explanation- (empty or
help) - General overview
Output Format
Default Overview (no argument or help)
+----------------------------------------------------------+
| PromptShield |
+----------------------------------------------------------+
COMMANDS
/ps:r <prompt> Review Mode - show improvements, ask approval
/ps:a <prompt> Auto Mode - improve and execute immediately
/ps:lint <prompt> LINT Mode - full diagnosis with test cases
/ps:build <goal> BUILD Mode - design new prompt from requirements
/ps:help [topic] This help (topics: commands, lint, build, 8point/7point)
QUICK START
1. Try: /ps:r Write a function to parse JSON
2. Review the score and suggested improvements
3. Type 'y' to accept, 'n' to reject, 'e' to edit
RECOMMENDED FLOW
New prompts: /ps:build → /ps:lint → iterate
Existing prompts: /ps:lint → /ps:r → approve
OUTPUT LEVELS
Default: score + top issues + improved prompt
Triggers for different detail levels:
- "간단히" / "quick" → Express (score + top3 only)
- "자세히" / "detail" → Full analysis with all sections
MORE INFO
/ps:help commands - All command details
/ps:help 8point - Scoring criteria explained (alias: 7point)
Topic: commands
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.
- 3d ago First seen · 313 lines · 9 tokens per session scan B 2155c9ea3031
help is a command published in the GitHub repository joseph0926/prompt-shield (5 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 2,190 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
brand-setup
Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.
save
Save this conversation as a new or existing reusable context.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
review
View your learning progress — quiz scores, weak areas, and what to study next.
standing
The sessions the-loop keeps for itself — declared in the CLI config, brought up by the-loop start, and addressed by name rather than by work item.