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 agents/microsoft/bcquality/instruction-structure-is-role-rules-stepsgit clone --depth 1 https://github.com/microsoft/BCQualityWrote 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/agents/microsoft/bcquality/instruction-structure-is-role-rules-steps)<a href="https://agentmods.dev/agents/microsoft/bcquality/instruction-structure-is-role-rules-steps"><img src="https://agentmods.dev/badge/agents/microsoft/bcquality/instruction-structure-is-role-rules-steps.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 | $0.00000 | $0.00277 |
| Opus 5 | $0.00000 | $0.00138 |
| Sonnet 5 | $0.00000 | $0.00055 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
instruction-structure-is-role-rules-steps 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.
What it actually says
Instruction documents use responsibilities, guidelines, then ordered steps
Description
The runtime treats instructions as the agent's standing prompt. A one-line goal produces inconsistent navigation. Microsoft's instruction framework is three layers: responsibilities (what the agent owns), guidelines (rules for every task), and instructions (ordered steps per task, with substeps). That structure is BC-specific, not generic prompt flavour.
Best Practice
Store a document that states responsibilities, then non-negotiable guidelines (when to request a review, when not to post), then numbered steps for each task. Keep that text in the resource you pass to SetInstructions.
See sample: instruction-structure-is-role-rules-steps.good.al.
Anti Pattern
A single sentence such as Check customer credit for the sales order. Detection signal: instruction resource or SetInstructions payload with no responsibilities / guidelines / steps sections.
See sample: instruction-structure-is-role-rules-steps.bad.al.
See also
instructions-describe-work-not-tool-ids.md and use-documented-instruction-keywords.md define how to write the steps inside this structure.
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 · 31 lines · 0 tokens per session scan A 93273f058303
instruction-structure-is-role-rules-steps is an agent published in the GitHub repository microsoft/BCQuality (204 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 277 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 2026-09-03.
Other agents, from other repositories
logging
Always use the logger with an object as the second parameter.
prompt-engineering-expert
Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…
rubber-duck-2.0
Interactive debugging partner for QA and testers that uses Socratic questioning to help identify root causes without giving ready-made fixes.
test-planner
An expert QA test planner agent that explores web applications and APIs to create comprehensive, risk-prioritized test plans.
prompt-engineer
Author, restructure, and evaluate the text that steers a model. TRIGGER WHEN: writing system prompts, designing agent instructions, or optimizing prompt performance for reliability and token efficiency.
hyv-veo-prompt-smith
The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…