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 instructions/savedpixel/ai-agent-rules-generator/ratelimittinggit clone --depth 1 https://github.com/savedpixel/ai-agent-rules-generatorWrote 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/instructions/savedpixel/ai-agent-rules-generator/ratelimitting)<a href="https://agentmods.dev/instructions/savedpixel/ai-agent-rules-generator/ratelimitting"><img src="https://agentmods.dev/badge/instructions/savedpixel/ai-agent-rules-generator/ratelimitting.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 | $0.00522 | $0.00522 |
| Opus 5 | $0.00261 | $0.00261 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
ai-agent-rules-generator ratelimitting.instructions.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 4d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rate Limit Prevention (CRITICAL)
You cannot recover from rate limits - the chat session will stop completely. Prevention is essential. Do NOT ask for confirmation - work autonomously but cautiously.
Rules
- Be concise: Keep responses short and to the point. Avoid verbose explanations.
- Don't repeat back: Don't echo the user's request or repeat code they've already shared.
- Plan first: Before making ANY tool calls, create a complete mental plan. Identify the minimum number of calls needed.
- Absolute minimum tool calls: Only make tool calls that are strictly necessary.
- Batch aggressively: Combine multiple operations into single requests wherever possible.
- Reuse information: Never re-fetch data you already have from earlier in the conversation.
- No exploratory calls: No speculative searches or "just checking" requests.
- Checkpoint silently: After significant work, briefly note what's done so progress isn't lost if the session breaks.
- If uncertain: Make a reasonable decision and proceed - do not ask me to confirm.
- Max 2 tool calls per response: Never make more than 2 tool calls in a single response. Complete the response, then continue in the next one.
Output Length Limits
Responses that are too long will be cut off and fail. Stay within limits.
- Max ~300 lines per response: If output would exceed this, split across multiple responses.
- One file at a time: When generating or editing multiple files, output one file per response, then continue.
- Truncate examples: Show only essential code snippets, not full files unless requested.
- Use summaries: For large changes, summarize what was done instead of showing everything.
- Continue automatically: If you need to split output, end with
... continuingand proceed in the next response without asking.
Visibility
When you take any rate-limit prevention action, output a short status line so I can monitor:
📦 BATCH: [what was combined]- when combining multiple operations♻️ REUSE: [what data]- when reusing data instead of re-fetching⏭️ SKIP: [what was skipped]- when skipping an unnecessary call💾 CHECKPOINT: [progress summary]- when saving progress state✂️ SPLIT: [what's being split]- when breaking output into multiple responses
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.
- 4d ago First seen · 41 lines · 522 tokens per session scan A f830f5ade197
ai-agent-rules-generator ratelimitting.instructions.md is an instructions file published in the GitHub repository savedpixel/ai-agent-rules-generator (7 stars, last pushed 4mo ago), licensed MIT. It adds 522 tokens to every session, about $0.0026 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 instructions, from other repositories
copilot-setting AGENTS.md
AGENTS.md instructions for zexion7873/copilot-setting, covering copilot-setting — agent guide, communication language, repository purpose, validation commands and architecture.
copilot-setting java.instructions.md
Load when writing or reviewing .java code — Java 8 version-lock floor: syntax, exceptions, logging, concurrency. Triggers on: var, records, text blocks, List.of/Map.of, pattern matching, java.time, BigDecimal, SLF4J. Forces Java 8, not modern Java. Defer SQL/Spring/JSP to their files.
copilot-setting spring-hibernate.instructions.md
Load when writing or reviewing Java or hbm.xml on a Spring 3.2 + Hibernate 4.2 stack — native Session API, XML mappings/tx, Spring MVC. Triggers on: getCurrentSession (not openSession), hbm.xml (not JPA @Entity), (not @Transactional), @Controller/@RequestMapping (not @GetMapping). No Spring Boot/JPA. Defer SQL to…
copilot-setting sql-ddl.instructions.md
Load when writing or reviewing MySQL DDL or migration scripts — CREATE/ALTER TABLE, indexes, stored procedures, backfills. Triggers on: ALTER TABLE, ALGORITHM=INSTANT/INPLACE, online schema change (pt-osc, gh-ost), rollback scripts, chunked backfill, DROP COLUMN, sp stored procedures. MySQL 8.0 / InnoDB. Query and…
copilot-setting xml-config.instructions.md
Load when writing or reviewing stack XML — Spring applicationContext, hbm.xml, web.xml, or Maven pom.xml. Triggers on: (not ), spring-beans-3.2.xsd (not 4.0), , DispatcherServlet, , scope test/provided, source/target 1.8, no -SNAPSHOT/LATEST. No Spring Boot. Defer SQL/Java to their files.
copilot-setting sql.instructions.md
Load when writing or reviewing SQL in Java code — JDBC DAOs, HQL, query tuning. Triggers on: PreparedStatement/? (no concat), :paramName, no SELECT , WHERE on UPDATE/DELETE, indexes, EXPLAIN. Raw JDBC, not Spring Boot. DDL/migrations: sql-ddl.instructions.md. Defer Hibernate queries to spring-hibernate.instructions.md.