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 loggit 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/log)<a href="https://agentmods.dev/skills/lemon-etvibe/prompt-vault/log"><img src="https://agentmods.dev/badge/skills/lemon-etvibe/prompt-vault/log/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/log"><img src="https://agentmods.dev/badge/skills/lemon-etvibe/prompt-vault/log.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 | $0.00063 | $0.00694 |
| Opus 5 | $0.00032 | $0.00347 |
| Sonnet 5 | $0.00013 | $0.00139 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
log 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record completed work from the current conversation session as a phase log.
Procedure
-
Verify
.local/logs/directory exists (create if missing) -
Determine next phase number from existing
phase-*.mdfile count (3-digit zero-padded) -
Write
phase-NNN.mdin the following format:# Phase NNN: $ARGUMENTS (or auto-inferred title) - **Date**: YYYY-MM-DD - **Session**: (session ID or timestamp) - **Trigger**: manual ## User Prompt > Record the user's original request as close to verbatim as possible ## Actions - List major actions performed by Claude in chronological order - Include tools used, files read, files created/modified ## Results - Summary of deliverables (generated file paths, key findings) - Key data or metrics ## Decisions - Decisions made and their rationale ## Next - Next steps or open items -
Update
.local/logs/_index.md: add/update the phase row| NNN | Title | done | YYYY-MM-DD | One-line summary | -
Update auto-log state file (
.local/logs/last-log-state.json) to prevent auto-logger duplication: — WHY: 자동 로거(Stop/PreCompact 훅)가 같은 내용을 중복 기록하지 않도록- Compute transcript hash via Bash:
Prefix withshasum -a 256 ~/.claude/projects/.../SESSION_ID.jsonl | cut -d' ' -f1sha256:to form"sha256:<hex>" - Write state:
{ "lastLogTimestamp": <current_timestamp_ms>, "lastTranscriptHash": "sha256:<hash>", "lastLogTurnCount": <total_turn_count>, "lastPhaseNumber": "<NNN>", "lastTrigger": "manual" } - This ensures the auto-logger (Stop/PreCompact hooks) won't re-log the same content
- Compute transcript hash via Bash:
-
Output completion message (bilingual based on
langin.local/logs/.config):- en: "✅ Phase NNN logged."
- ko: "✅ Phase NNN 기록 완료."
Example
Input: /prompt-vault:log 로그인 버그 수정
Output (phase-003.md):
# Phase 003: 로그인 버그 수정
- **Date**: 2026-03-12
- **Session**: abc123
- **Trigger**: manual
## User Prompt
> 로그인 시 null 에러 수정해줘
## Actions
- Read: src/auth.ts
- Edit: src/auth.ts — null 체크 추가
...
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.
- 9d ago First seen · 89 lines · 63 tokens per session scan A 9a1a563a60f1
log is a skill published in the GitHub repository lemon-etvibe/prompt-vault (2 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 694 once invoked, about $0.0003 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 skills, from other repositories
sitrep
Situational awareness — where am I, what was I doing, what's next. Context recovery after compression, confusion, or mid-session reorientation.
caveman
Ultra-compressed mode — 65-75% fewer tokens, preserving technical accuracy. Strips filler, hedging, pleasantries. Code/commits stay in normal language.
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
txt-copy
Copy generated text content to clipboard. Use when user asks to "copy this", "copy to clipboard", "save to clipboard", or after creating emails, messages, letters, or other text content that needs to be shared.
docs
Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…
sitrep-panel
Keep a live local HTML report updated as you work on a task — a status board, a running "what's happening now" narrative, screenshots, and a newest-first log — served on localhost so the user can watch progress in a browser tab instead of reading the transcript. Use when the user invokes /sitrep-panel, asks for a…