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/browsetoolsgit clone --depth 1 https://github.com/savedpixel/ai-agent-rules-generatorWhat 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 | $0.00490 | $0.00490 |
| Opus 5 | $0.00245 | $0.00245 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
ai-agent-rules-generator browsetools.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 2d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevTools Verification Rules
MANDATORY: Browser Verification Before Completion
After every new feature, bug fix, or change that touches the UI or frontend behavior, you MUST verify the change works using Chrome DevTools MCP tools before marking it as complete.
Required Verification Steps
- Visual verification — Use
take_screenshotto confirm the page renders correctly. - Console check — Use
list_console_messagesto confirm there are no JS console errors. - Functional test — Use
click,fill, and other interaction tools to test the changed behavior end-to-end. - State check — Use
evaluate_scriptto inspect DOM values or framework state when needed. - Regression check — Take screenshots of adjacent/related views to ensure no regressions.
Completion Gate
- Only after successful verification may you mark the task as completed.
- If verification fails, fix the issue and re-verify before completing.
- Do NOT mark any UI task as done until it has been tested and confirmed working.
Dev Server Prerequisite
Before browser verification, ensure the WordPress dev environment is running:
cd /path/to/glitch-woocommerce-gateway && wp-env start
The WordPress admin runs at http://localhost:8888/wp-admin/. The storefront runs at http://localhost:8888/. Navigate to the relevant page before taking screenshots or interacting.
Do not kill the server after you finished browsing, keep it alive so that the user can still work on it.
Key Pages for Verification
- Admin Settings:
http://localhost:8888/wp-admin/admin.php?page=wc-settings&tab=checkout§ion=glitch_gateway - Checkout Page:
http://localhost:8888/checkout/ - Order Admin:
http://localhost:8888/wp-admin/edit.php?post_type=shop_order
Authentication Credentials
The WordPress dev environment requires login before accessing admin pages. Use these credentials:
- Username:
admin - Password:
password
After navigating to any admin URL, if redirected to a login page, fill in the credentials above and submit before proceeding with verification.
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.
- 2d ago First seen · 52 lines · 490 tokens per session scan A 854debc5814d
ai-agent-rules-generator browsetools.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 490 tokens to every session, about $0.0024 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
loadout playwright-python.instructions.md
Playwright Python Test Generation Instructions.
loadout playwright-typescript.instructions.md
Playwright TypeScript Test Generation Instructions.
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…