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/ivangrynenko/cursorrules/session-summarygit clone --depth 1 https://github.com/ivangrynenko/cursorrulesWhat 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 | $0.00000 | $0.00588 |
| Opus 5 | $0.00000 | $0.00294 |
| Sonnet 5 | $0.00000 | $0.00118 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
session-summary 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Custom Command: Session Summary
Command Usage
/session-summary [notes]
Use optional notes to highlight areas you want analysed.
You are an AI assistant tasked with analyzing a coding session and suggesting improvements to the AGENTS.md file. Your goal is to enhance the efficiency of tool calls and reduce future token usage by identifying and addressing problems that occurred during the session.
First, review the current content of the AGENTS.md file:
<agents_md_content> the current AGENTS.md content </agents_md_content>
Now, examine the session history:
<session_history> the full session history transcript </session_history>
Analyze the session history and generate improvement suggestions for the AGENTS.md file. Focus on the following areas:
- Failed tool calls
- Repeated attempts to use non-existing tools or options
- Incorrect decisions leading to wasted tokens
- Attempts to write to files outside permitted directories
- Any other issues that resulted in inefficient token usage
When creating suggestions, keep them small and concise. Each suggestion should directly address a specific problem identified in the session history.
Format your suggestions as follows:
- Start each suggestion with "Suggestion: " followed by a brief description of the improvement.
- Provide a short explanation of why this improvement is necessary, referencing the specific issue in the session history.
- If applicable, include the exact text to be added to or modified in the AGENTS.md file.
Present your suggestions in a numbered list, allowing the user to choose which ones to implement. For example:
-
Suggestion: Add permitted directory paths Explanation: Multiple attempts were made to write to unauthorized directories, wasting tokens. Addition to AGENTS.md: "Permitted write directories: /project/data, /project/output"
-
Suggestion: Update available tool list Explanation: Several calls were made to non-existent tools, causing errors and token waste. Modification in AGENTS.md: Replace "analyze_data" with "process_data" in the tools section.
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 · 62 lines · 0 tokens per session scan A 33cb64e4b102
session-summary is a command published in the GitHub repository ivangrynenko/cursorrules (87 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 588 tokens. 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 2026-08-30.
Other commands, from other repositories
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
matcha:audit
🍵 Stack health check — find overlaps, waste, and risks before they become problems.
create-pr
Create a Pull Request from the current branch targeting develop, with correct PRJ-XXX title format, Jira link in the body, and optional Jira status sync.
typescript
Apply TypeScript best practices and coding standards.
fix-issue
Command "fix-issue" from HKTITAN/cursor-best-practices, covering steps and rules.
learn
Analyze the current session and extract any patterns worth saving as skills.