Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ronmkr/PromptBooknpx agentmods add skills/ronmkr/promptbook/memory-instruction-refinementWrote 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/ronmkr/promptbook/memory-instruction-refinement)<a href="https://agentmods.dev/skills/ronmkr/promptbook/memory-instruction-refinement"><img src="https://agentmods.dev/badge/skills/ronmkr/promptbook/memory-instruction-refinement.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 5.1 | $0.00079 | $0.01464 |
| Opus 5 | $0.00039 | $0.00732 |
| Sonnet 5 | $0.00016 | $0.00293 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
gemini-md-improver 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 6d 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.
This is a copy
88% identical to claude-md-improver — 50 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md Improver
Audit, evaluate, and improve GEMINI.md files across a codebase to ensure Antigravity has optimal project context.
This skill can write to GEMINI.md files. After presenting a quality report and getting user approval, it updates GEMINI.md files with targeted improvements.
Workflow
Phase 1: Discovery
Find all GEMINI.md files in the repository:
find . -name "GEMINI.md" -o -name ".gemini.md" -o -name ".gemini.local.md" 2>/dev/null | head -50
File Types & Locations:
| Type | Location | Purpose |
|---|---|---|
| Project root | ./GEMINI.md |
Primary project context (checked into git, shared with team) |
| Local overrides | ./.gemini.local.md |
Personal/local settings (gitignored, not shared) |
| Global defaults | ~/.gemini/GEMINI.md |
User-wide defaults across all projects |
| Package-specific | ./packages/*/GEMINI.md |
Module-level context in monorepos |
| Subdirectory | Any nested location | Feature/domain-specific context |
Note: Gemini auto-discovers GEMINI.md files in parent directories, making monorepo setups work automatically.
Phase 2: Quality Assessment
For each GEMINI.md file, evaluate against quality criteria. See references/quality-criteria.md for detailed rubrics.
Quick Assessment Checklist:
| Criterion | Weight | Check |
|---|---|---|
| Commands/workflows documented | High | Are build/test/deploy commands present? |
| Architecture clarity | High | Can Gemini understand the codebase structure? |
| Non-obvious patterns | Medium | Are gotchas and quirks documented? |
| Conciseness | Medium | No verbose explanations or obvious info? |
| Currency | High | Does it reflect current codebase state? |
| Actionability | High | Are instructions executable, not vague? |
Quality Scores:
- A (90-100): Comprehensive, current, actionable
- B (70-89): Good coverage, minor gaps
- C (50-69): Basic info, missing key sections
- D (30-49): Sparse or outdated
- F (0-29): Missing or severely outdated
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 180 lines · 79 tokens per session scan A f250317838ae
gemini-md-improver is a skill published in the GitHub repository ronmkr/PromptBook (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,464 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to claude-md-improver, differing in 50 lines, and is treated as a copy.
Other skills, from other repositories
knowledge-session-state-and-context-session-catalog-fork-rewind-and-export
覆盖 durable Session 的发现分页、归档恢复、稳定加载、分叉、user-turn rewind、历史搜索和安全 Markdown 导出。 适用于修改 SessionService、catalog cursor、lineage、archive、fork、rewind、TranscriptSearch 或 export 行为。 不含实时 turn/mailbox 恢复（见 ../active-turn-interactions-and-recovery/）和底层事件写入协议（见 ../durable-transcript-and-event-projection/）。 关键词：SessionService…
knowledge-session-state-and-context-compaction-pipeline-and-checkpoints
覆盖 Token 占用投影、70% handoff、micro/snip/LLM/fallback 压缩、context-limit 恢复和 replacement checkpoint。 适用于修改压缩阈值、摘要重试、continuation ledger、工具结果预算、保留证据或 Provider overflow 恢复。 不含项目级 Auto Memory（见 ../project-auto-memory/）和完整 transcript/replay（见 ../../durable-transcript-and-event-projection/）。 关键词：CompactionService…
knowledge-session-state-and-context
覆盖会话状态所有权、持久事件、读侧投影、历史分叉/回退、活动轮次恢复及模型上下文压缩。 适用于修改 Session 生命周期、JSONL/CQRS、resume/fork/rewind、steering、Token 预算或项目记忆。 不含 Agent 决策循环（见 ../agent-execution-and-orchestration/）和工具执行机制（见 ../tool-and-automation-platform/）。 关键词：SessionRuntime, SessionService, PersistentStore, SessionEventLog, JSONL, CQRS, compaction, rewind…
session-search
For CLI agents WITHOUT subagent support (e.g., Codex CLI). Search previous code agent sessions for specific work, decisions, or code patterns.
context
Working-state snapshot guidance. Restates task/files/decisions in one block so state survives context compaction. Compaction timing is the host's job.
gno
Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…