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/thiagoguislotti/copilot-instructions/subagent-planning-workflowgit clone --depth 1 https://github.com/ThiagoGuislotti/copilot-instructionsWrote 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/instructions/thiagoguislotti/copilot-instructions/subagent-planning-workflow)<a href="https://agentmods.dev/instructions/thiagoguislotti/copilot-instructions/subagent-planning-workflow"><img src="https://agentmods.dev/badge/instructions/thiagoguislotti/copilot-instructions/subagent-planning-workflow.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 5.1 | $0.01884 | $0.01884 |
| Opus 5 | $0.00942 | $0.00942 |
| Sonnet 5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
copilot-instructions subagent-planning-workflow.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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub-Agent Planning Workflow
Purpose
- Standardize how the Super Agent lifecycle plans, routes, executes, reviews, and closes out non-trivial work with a deterministic sub-agent chain.
- Keep planning artifacts versioned under
planning/when the workspace owns that surface, and fall back to.build/super-agent/when it does not.
Planning Workspace Contract
- When the workspace provides
planning/README.md, use it as the planning workspace guide. - Active plans live in
planning/active/when the workspace provides a versioned planning surface; otherwise they live in.build/super-agent/planning/active/. - Finished plans move to
planning/completed/or.build/super-agent/planning/completed/only when the work is genuinely complete. - When the workspace provides
planning/specs/README.md, use it as the versioned specification guide for brainstorming/spec artifacts. - Active specs live in
planning/specs/active/when the workspace provides a versioned spec surface; otherwise they live in.build/super-agent/specs/active/. - Finished specs move to
planning/specs/completed/or.build/super-agent/specs/completed/with the related workstream when applicable. - Plan files should use stable slugged names such as
plan-<scope>.md. - Reuse and update an existing active plan when the request continues the same workstream instead of creating a duplicate file.
Dating Policy (Mandatory)
Planning artifacts are the primary continuity mechanism across context resets, session boundaries, and agent handoffs. Dates make it safe to resume after any interruption.
- Every plan must include a
Generated: YYYY-MM-DD HH:mmat the top. - Every task or step entry must carry a
[YYYY-MM-DD HH:mm]prefix when it is created, updated, or completed. - When a task is completed, append
✓ [YYYY-MM-DD HH:mm]— never remove the original creation timestamp. - When a task is in progress, mark it
[YYYY-MM-DD HH:mm IN PROGRESS]. - When a task is blocked, append
⚠ blocked [YYYY-MM-DD HH:mm]: <reason>. - The plan status block must include a
LastUpdated: YYYY-MM-DD HH:mmfield updated on every change. - A plan without timestamps on its tasks cannot be used as a reliable resume point — treat undated tasks as unverified.
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.
- 5d ago First seen · 124 lines · 1,884 tokens per session scan A 3ece25cf59c4
copilot-instructions subagent-planning-workflow.instructions.md is an instructions file published in the GitHub repository ThiagoGuislotti/copilot-instructions (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,884 tokens to every session, about $0.0094 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
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
langchain AGENTS.md
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.