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/fusengine/agents/prompt-historygit clone --depth 1 https://github.com/fusengine/agentsWrote 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/fusengine/agents/prompt-history)<a href="https://agentmods.dev/commands/fusengine/agents/prompt-history"><img src="https://agentmods.dev/badge/commands/fusengine/agents/prompt-history.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 | $0.00007 | $0.01294 |
| Opus 5 | $0.00003 | $0.00647 |
| Sonnet 5 | $0.00001 | $0.00259 |
| Haiku 4.5 | $0.00001 | $0.00129 |
Grade A, and why
prompt-history 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.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prompt history
Command for managing prompt history and versioning.
Usage
/prompt history [action] [options]
Actions
| Action | Description |
|---|---|
list |
List all saved prompts |
show <id> |
Display a specific prompt |
search <query> |
Search by keyword |
diff <id1> <id2> |
Compare two versions |
rollback <id> |
Restore a previous version |
export |
Export history |
clean |
Clean old versions |
Storage
Prompts are saved in:
~/.claude/prompt-history/
├── index.json # Prompt index
└── prompts/
├── 2025-01-21_code-reviewer_v1.md
├── 2025-01-21_code-reviewer_v2.md
└── 2025-01-22_support-assistant_v1.md
Index Format
{
"version": "1.0",
"prompts": [
{
"id": "prompt_001",
"name": "code-reviewer",
"versions": [
{
"version": 1,
"date": "2025-01-21T10:30:00Z",
"file": "2025-01-21_code-reviewer_v1.md",
"hash": "abc123",
"notes": "Initial version"
},
{
"version": 2,
"date": "2025-01-21T14:00:00Z",
"file": "2025-01-21_code-reviewer_v2.md",
"hash": "def456",
"notes": "Added security section",
"parent": 1
}
],
"tags": ["code", "review", "quality"],
"category": "agents"
}
]
}
Examples
List History
/prompt history list
Output:
## Prompt History
| ID | Name | Versions | Last Modified | Tags |
|----|------|----------|---------------|------|
| prompt_001 | code-reviewer | 3 | 2025-01-21 | code, review |
| prompt_002 | support-assistant | 2 | 2025-01-20 | support |
| prompt_003 | summarizer | 1 | 2025-01-19 | text |
Total: 3 prompts, 6 versions
View a Prompt
/prompt history show prompt_001
Output:
## code-reviewer (prompt_001)
**Category**: agents
**Tags**: code, review, quality
**Versions**: 3
### Version History
| V | Date | Notes | Hash |
|---|------|-------|------|
| 3 | 2025-01-21 14:00 | Added OWASP | def456 |
| 2 | 2025-01-21 12:00 | Added SOLID | abc123 |
| 1 | 2025-01-21 10:00 | Initial version | 789xyz |
### Current Content (v3)
---
[Prompt content]
---
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 · 247 lines · 7 tokens per session scan A 1b811312435e
prompt-history is a command published in the GitHub repository fusengine/agents (25 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 1,294 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 2026-09-03.
Other commands, from other repositories
launch-an-ai-feature
Workflow recipe — take an AI/LLM feature from a probabilistic-aware PRD to a launch-ready model card by chaining 5 skills.
fix-prompt
Fix and improve a rough prompt — show the cleaned version and the changes before acting on it.
test-prompt
Test an AI prompt against multiple scenarios to verify consistent, quality output.
setup-agents
Scaffold a multi-agent AI setup for any repo. Scans the codebase, interviews the developer, generates agent configs for whichever AI tools the repo uses (Copilot, Claude Code, Cursor, Codex, Windsurf). Use when asked to "set up agents", "scaffold Copilot agents", or "create an AGENTS.md".
briefing-claude
Use when Claude keeps building the wrong UI and you are re-rolling prompts. How to write the brief, which references and constraints to give, how to iterate instead of starting over, and how to spot when it is guessing.
on
Turn on senior mode — refuses vague questions, hints instead of answers, never writes code.