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/stefaniuk/loadout/copilot-instructionsgit clone --depth 1 https://github.com/stefaniuk/loadoutWhat 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 | $0.00555 | $0.00555 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
loadout copilot-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 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions
This file is the authoritative instruction source for routine GitHub Copilot work in this repository. Use it as the operational default. Consult the constitution directly when a task affects specifications, behaviour, architecture, ADRs, or governance, or when guidance conflicts.
Implementation discipline
- Do not invent requirements or widen scope.
- Keep outputs deterministic, make side effects explicit, and surface errors.
- If code and specification diverge, either fix the implementation or amend the specification with rationale.
- Order code to follow the primary execution or call flow when that improves readability, and group widely shared utilities clearly.
Test-driven development
- For behavioural changes, follow
Red -> Green -> Refactor. - Use property-based testing where it adds value.
Skill invocation gates
- Use the
test-driven-developmentskill only when the task requires a new failing test that should drive a code or behaviour change. - On unexpected test, build, or runtime failures, load the
systematic-debuggingskill. - Before completion, load the
verification-before-completionskill.
Workflow mode
- Resolve the active workflow mode with
make workflow-statusbefore invoking lifecycle skills. - If the mode is
speckit, use only thespeckit-*lifecycle skills for that session or worktree. - If the mode is
superpowers, use only the imported Superpowers workflow skills for that session or worktree. - Do not mix the Speckit and Superpowers lifecycle commands in the same session or worktree.
- Switch explicitly with
make workflow-use mode=speckitormake workflow-use mode=superpowers, then start a fresh chat session.
Repository verification policy
The Stop hook is the canonical enforcement for local quality gates. When that hook is active, do not rerun the same commands manually unless diagnosing a failure or the hook is unavailable.
Communication style
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 · 54 lines · 555 tokens per session scan A fc82f9baa722
loadout copilot-instructions.md is an instructions file published in the GitHub repository stefaniuk/loadout (1 stars, last pushed 4d ago), licensed MIT. It adds 555 tokens to every session, about $0.0028 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
apm cli.instructions.md
CLI Design Guidelines for visual output, styling, and user experience standards.
apm cicd.instructions.md
CI/CD Pipeline configuration for PyInstaller binary packaging and release workflow.
apm encoding.instructions.md
Cross-platform encoding rules — keep all source and CLI output within printable ASCII.
apm changelog.instructions.md
Changelog format and conventions based on Keep a Changelog.
featherspec AGENTS.md
Instructions for GregorBiswanger/featherspec, covering featherspec — constitution (spec-driven development), single source of truth (do not duplicate), non-negotiables, progress & state sync (gate) and fast path.
spec-driven-steroids AGENTS.md
Instructions for lindoelio/spec-driven-steroids, covering agents.md, project identity, technology stack, essential commands and agent constraints.