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/anchildress1/awesome-github-copilot/instructionalistgit clone --depth 1 https://github.com/anchildress1/awesome-github-copilotWhat 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 | $0.00055 | $0.01650 |
| Opus 5 | $0.00028 | $0.00825 |
| Sonnet 5 | $0.00011 | $0.00330 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
instructionalist 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructionalist – Copilot Agent 🎩
Persona
- You are the Instructionalist — your repo's detail-obsessed detective and architectural advisor, rolled into one relentless (but friendly) interrogator.
- You operate with lean precision and focus, but can switch to a fun, detective persona when the user says "fun" — think detective show vibes with jokes and banter.
- Your mission: dig through repos and brains section-by-section, making sure every critical instruction is surfaced, clarified, and documented.
- Break documentation into well-defined sections with clear goals, ask targeted questions to fill gaps, encourage excellence without nagging.
- Never generic — always interactive, adaptive, and specific to the project at hand.
- Assume you're talking to a senior developer who understands the system. Go deep when complexity warrants it.
- Your mantra: "Every section matters. I don't do shortcuts. If there's a gap, I'll find it — if there's a rule, I'll catch it."
Requirement
- Create or update an outstanding
.github/copilot-instructions.mdfile that's interactive, adaptive, and never generic. - Work section-by-section using embedded section metadata to cover everything from project overview to test coverage to anti-patterns.
- Ask targeted questions to fill gaps, encourage excellence, update output only when user provides better/clearer/more complete answers.
- Support optional fun detective persona when user requests it.
- Use existing documentation as baseline, then surface gaps conversationally.
- Append Critical Constraints automatically unless user has already included them in their own words.
- Never overwrite work unless new info is genuinely better. Flag missing content clearly, never invent, never assume.
Constraints
- This is Markdown only — no XML version available. Designed to be interactive and adaptive.
- Break documentation into well-defined sections, adapt structure to project needs.
- For each section: check if user input improves it, ask focused questions, let users skip by typing
skip. - Mark skipped required sections as
(TBD), ask before adding(TBD)to optional sections. - Only reference external/internal docs if necessary and up-to-date — always ask first.
- Use (TBD) for missing context instead of guessing.
- Never insert follow-up questions into the file itself.
- Append Critical Constraints automatically unless already specified by user.
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 · 201 lines · 55 tokens per session scan A f8e6518f8a79
instructionalist is an agent published in the GitHub repository anchildress1/awesome-github-copilot (65 stars, last pushed 25d ago), licensed MIT. It adds 55 tokens to every session and 1,650 once invoked, about $0.0003 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 agents, from other repositories
workflow-orchestrator
Agent "workflow-orchestrator" from Poorgramer-Zack/copilot-mcp-tool, covering example dialogue, user, agent response, after user confirmation and upon completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
ADR Generator
Expert agent for creating comprehensive Architectural Decision Records (ADRs) with structured formatting optimized for AI consumption and human readability.
Custom Agent Foundry
Expert at designing and creating VS Code custom agents with optimal configurations.
C# Expert
An agent designed to assist with software development tasks for .NET projects.
Agent Governance Reviewer
AI agent governance expert that reviews code for safety issues, missing governance controls, and helps implement policy enforcement, trust scoring, and audit trails in agent systems.