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/chsami/microbot/agents-mdgit clone --depth 1 https://github.com/chsami/MicrobotWhat 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 | $0.00648 | $0.00648 |
| Opus 5 | $0.00324 | $0.00324 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
Microbot AGENTS.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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microbot
RuneLite fork with a hidden always-on plugin hosting automation scripts. Composite Gradle build, Java 11 target (JDK 17+ to develop).
Build / validate
- Compile:
./gradlew :client:compileJava - Full:
./gradlew buildAll - Shaded jar:
./gradlew :client:assemble - Tests (opt-in):
:client:runUnitTests,:client:runTests,:client:runIntegrationTest(needs running game)
Non-negotiable rules
- Never instantiate caches/queryables directly — use
Microbot.getRs2XxxCache().query()/.getStream(). Seerunelite-client/src/main/java/net/runelite/client/plugins/microbot/api/QUERYABLE_API.md. - Never block/sleep on the client thread.
- Never use static sleeps to wait for game state — use
sleepUntil(condition, timeoutMs). - Keep
MicrobotPluginhidden/always-on; don't break its config panel wiring. - Respect existing Checkstyle/Lombok patterns; don't weaken security (telemetry tokens, HTTP clients).
- Minimal logging; no PII or session identifiers.
Review priority
- P0: client crashes, client-thread blocking, login/world-hop breakage, cache invariant corruption, credential/token exposure.
- P1: script loop timing, overlay correctness, plugin discovery/config, shaded-jar packaging, build reproducibility.
Runtime tooling
./microbot-cli(JSON output) — seedocs/MICROBOT_CLI.md, HTTP APIdocs/AGENT_SERVER.md, full tool listdocs/AGENT_SCRIPT_TOOLS.md.- Agent Server plugin runs on port 8081 by default.
- Offline client-thread lookup:
./microbot-cli ct <method>. - Test mode:
-Dmicrobot.test.mode=true -Dmicrobot.test.script=<PluginName>→ results in~/.runelite/test-results/. Protocol:docs/AGENTIC_TESTING_LOOP.md.
In-game settings
Use the settings search bar — tab indices shift on updates. Verify changes via ./microbot-cli varbit <id>.
Before touching microbot/util/
Read docs/entity-guides/README.md. Add a gotcha there when you fix an entity-assumption bug.
Docs maintenance
- Keep root
README.md,docs/README.md, anddocs/INDEX.mdshort routing pages. - Put volatile command details, API examples, endpoint lists, generated inventories, and screenshots in the narrowest owning doc.
- Prefer links to owner docs over copying the same guidance into multiple high-level files.
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 · 45 lines · 648 tokens per session scan A 495867ac0fb4
Microbot AGENTS.md is an instructions file published in the GitHub repository chsami/Microbot (205 stars, last pushed 3d ago), licensed BSD-2-Clause. It adds 648 tokens to every session, about $0.0032 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 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.