revise-claude-md

revise-claude-md is a command for Claude Code from ronmkr/PromptBook. It costs 10 tokens per session (342 once invoked), scanned A, original, Apache-2.0.

A procedure for recording useful session lessons in GEMINI.md, a project instruction file for future Gemini coding sessions. It covers commands, coding patterns, tests, configuration details, and warnings.

In plain words
What is it for?
It helps find relevant GEMINI.md files, draft concise additions, explain proposed changes, and request approval before applying them.
Why use it?
It preserves recurring knowledge so later sessions can work with the codebase more effectively instead of rediscovering the same details.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Gemini CLI.

Good fit It helps find relevant GEMINI.md files, draft concise additions, explain proposed changes, and request approval before applying them.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ronmkr/promptbook/revise-claude-md
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ronmkr/PromptBook

Made for: Claude Code.

Wrote 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.

agentmods badge for revise-claude-md

README.md
[![agentmods](https://agentmods.dev/badge/commands/ronmkr/promptbook/revise-claude-md/github.svg)](https://agentmods.dev/commands/ronmkr/promptbook/revise-claude-md)
Your own site
<a href="https://agentmods.dev/commands/ronmkr/promptbook/revise-claude-md"><img src="https://agentmods.dev/badge/commands/ronmkr/promptbook/revise-claude-md/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.

agentmods 80×15 button for revise-claude-md

Your own site · 80×15
<a href="https://agentmods.dev/commands/ronmkr/promptbook/revise-claude-md"><img src="https://agentmods.dev/badge/commands/ronmkr/promptbook/revise-claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 342 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00010 $0.00342
Opus 5 $0.00005 $0.00171
Sonnet 5 $0.00002 $0.00068
Haiku 4.5 $0.00001 $0.00034

Measured 10d ago against content hash 0e2fa5383c21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

revise-claude-md 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 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.

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.

core/memory/commands/revise-claude-md.md · 55 lines

What it actually says

Review this session for learnings about working with Antigravity in this codebase. Update GEMINI.md with context that would help future Gemini sessions be more effective.

Step 1: Reflect

What context was missing that would have helped Gemini work more effectively?

  • Bash commands that were used or discovered
  • Code style patterns followed
  • Testing approaches that worked
  • Environment/configuration quirks
  • Warnings or gotchas encountered

Step 2: Find GEMINI.md Files

find . -name "GEMINI.md" -o -name ".gemini.local.md" 2>/dev/null | head -20

Decide where each addition belongs:

  • GEMINI.md - Team-shared (checked into git)
  • .gemini.local.md - Personal/local only (gitignored)

Step 3: Draft Additions

Keep it concise - one line per concept. GEMINI.md is part of the prompt, so brevity matters.

Format: <command or pattern> - <brief description>

Avoid:

  • Verbose explanations
  • Obvious information
  • One-off fixes unlikely to recur

Step 4: Show Proposed Changes

For each addition:

### Update: ./GEMINI.md

**Why:** [one-line reason]

\`\`\`diff
+ [the addition - keep it brief]
\`\`\`

Step 5: Apply with Approval

Ask if the user wants to apply the changes. Only edit files they approve.

Changes

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.

  1. 10d ago First seen · 55 lines · 10 tokens per session scan A 0e2fa5383c21

Subscribe to this mod's changes

revise-claude-md is a command published in the GitHub repository ronmkr/PromptBook (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 342 once invoked, about $0.0001 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.