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 skills add lemon-etvibe/prompt-vault --skill reportgit clone --depth 1 https://github.com/lemon-etvibe/prompt-vaultWrote 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/skills/lemon-etvibe/prompt-vault/report)<a href="https://agentmods.dev/skills/lemon-etvibe/prompt-vault/report"><img src="https://agentmods.dev/badge/skills/lemon-etvibe/prompt-vault/report/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/skills/lemon-etvibe/prompt-vault/report"><img src="https://agentmods.dev/badge/skills/lemon-etvibe/prompt-vault/report.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 | $0.00043 | $0.00565 |
| Opus 5 | $0.00022 | $0.00282 |
| Sonnet 5 | $0.00009 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade B, and why
report scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
SCRIPT_PATH=$(find ~/.claude/plugins -name "generate-report.sh" -path "*/prompt-vault/*" 2>/dev/null | head -1) What it actually says
Generate HTML reports from phase logs using the shell script.
CRITICAL: NEVER generate HTML yourself. ALWAYS run the shell script below.
Procedure
Step 0: Locate the plugin root
Find the generate-report.sh script path:
SCRIPT_PATH=$(find ~/.claude/plugins -name "generate-report.sh" -path "*/prompt-vault/*" 2>/dev/null | head -1)
echo "SCRIPT_PATH=${SCRIPT_PATH}"
If SCRIPT_PATH is empty, stop and tell the user the plugin is not installed properly.
Step 1: Run the script
MUST execute this command — do NOT write HTML manually:
bash "${SCRIPT_PATH}" "${1:-all}"
Arguments: summary, detail, all (default), or omit for all.
The script generates exactly two files:
.local/logs/report-summary.html— Project summary dashboard.local/logs/report-detail.html— Phase-by-phase detailed chat log
Do NOT create report.html, report_detail.html, or any other filename.
Step 2: Verify output
ls -la .local/logs/report-summary.html .local/logs/report-detail.html
If either file is missing, report the error — do NOT generate HTML as fallback.
Step 3: Report to user
Read lang from .local/logs/.config (default: "ko").
- en:
✅ Report generated! - ko:
✅ 리포트 생성 완료!
Then show file paths and open command:
- Summary: .local/logs/report-summary.html
- Detail: .local/logs/report-detail.html
open .local/logs/report-summary.html
Custom Reports (custom argument only)
- Run the standard script first (Step 1 above).
- Ask the user what they want to customize.
- Read the generated HTML and modify per request.
- Save and inform paths.
Error Handling
.local/logs/not found → Guide user to run/prompt-vault:init- Script not found → Show the find command output and guide reinstall
- Script fails → Show error output, do NOT attempt manual HTML generation
.configmissing → Script uses defaults automatically
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.
- 10d ago First seen · 77 lines · 43 tokens per session scan B b6652b3a0acb
report is a skill published in the GitHub repository lemon-etvibe/prompt-vault (2 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 565 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
brainstorm
Interactive idea maturation — explore, research, shape raw ideas into actionable plans. Use when you have a rough idea and want to think it through.
sitrep
Situational awareness — where am I, what was I doing, what's next. Context recovery after compression, confusion, or mid-session reorientation.
fastapi
FastAPI best practices + Pydantic. Use when building or reviewing FastAPI APIs.
memory
Knowledge system ops — recall, pollinate, audit docs. Subcommands: recall, pollinate, review. Use for pattern queries, cross-client transfer, or audits.
rust-skills
Rust best practices — 179 rules across 14 categories for idiomatic, optimized Rust code.
ship
Ship a build — pre-flight checks, deploy, document, verify, monitor. Use when deploying code, publishing packages, or releasing.