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/use-documented-instruction-keywordsgit 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/use-documented-instruction-keywords)<a href="https://agentmods.dev/agents/microsoft/bcquality/use-documented-instruction-keywords"><img src="https://agentmods.dev/badge/agents/microsoft/bcquality/use-documented-instruction-keywords.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 | $0.00308 |
| Opus 5 | $0.00000 | $0.00154 |
| Sonnet 5 | $0.00000 | $0.00062 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
use-documented-instruction-keywords 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
Use the toolkit instruction keywords for review, mail, and memory
Description
The agent runtime looks for specific phrases: ask for assistance, request a review, reply, write an email, memorize, Set field, use lookup, Invoke action. Ordinary English such as get a human to look or remember this is weaker. Outbound reply and email always require review; that is platform policy, not optional tone.
Best Practice
In the instruction resource, use those keywords at the decision points: request a review before posting; write an email only after stating that outbound mail is reviewed; memorize values the later steps need. Pair Reply / Write an email with an explicit review sentence.
See sample: use-documented-instruction-keywords.good.al.
Anti Pattern
Inventing tool-like verbs (call Copilot, click Post_Promoted) or omitting request a review before posting. Detection signal: instruction text that says email the customer with no review keyword.
See sample: use-documented-instruction-keywords.bad.al.
See also
instruction-structure-is-role-rules-steps.md defines the containing document structure, while instructions-describe-work-not-tool-ids.md keeps outcomes independent of UI tool identifiers.
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 697922415cce
use-documented-instruction-keywords 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 308 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.…
prompt-compression-verifier
Verifies prompt compression quality. Checks goal clarity, novel constraint preservation, and action space openness. Flags over-specification and training-redundant content. Returns VERIFIED or ISSUESFOUND.
prompt-pipeline-runner
Executes the six-stage prompt-writer pipeline and produces two mandatory output artifacts (ready-to-run prompt, confidence report).
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…