agentleFS
VincentChuWaiChowVincentChuWaiChow/vanguard-frontier-agentic/.github/copilot-instructions.md

vanguard-frontier-agentic

Copilot instructions23 starsChanged 4 months agoApache-2.0View on GitHub

This repository is a curated marketplace for cloud, zero-trust, and compliance-aware AI workflows. This repo supports multiple harnesses without pretending they are identical.

The file

We split this copilot-instructions.md into the rules it gives an agent

10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Keep changes tightly scoped to the request.

    line 25
  2. Distinctive:

    Do not add secrets, credentials, tokens, tenant IDs, wallets, or customer data.

    line 26
  3. Distinctive:

    Prefer official docs and live evidence for cloud/compliance claims.

    line 27
  4. Distinctive:

    Treat destructive actions, broad permissions, and MCP mutation paths as high risk.

    line 28
  5. Distinctive:

    Update catalog metadata when adding, moving, or removing cataloged assets.

    line 29
  6. Very specific:

    If intentional changes are made under cataloged skills/, refresh the skill manifest with npm run manifest:write.

    line 30
  7. Very specific:

    Run npm run validate before finishing.

    line 31
  8. Distinctive:

    Keep portable logic in canonical/shared assets.

    line 37
  9. Distinctive:

    Keep harness-specific behavior in the correct adapter format.

    line 38
  10. Distinctive:

    Do not invent unsupported executable metadata fields.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 3,854 Copilot instructions files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
copilot-instructions.md

Vanguard Frontier Agentic repository instructions

This repository is a curated marketplace for cloud, zero-trust, and compliance-aware AI workflows.

What to optimize for

  • Evidence-backed guidance over confident guessing
  • Least privilege over convenience
  • Zero-trust design over implicit trust
  • Safe automation with approval, validation, and rollback paths
  • Clear separation between facts, assumptions, inference, and unknowns

Repo structure

  • skills/ = reusable workflows
  • agents/ = expert roles
  • rules/ = harness-specific instructions
  • mcp/ = MCP references and trust notes
  • catalog/ = machine-readable indexes
  • schemas/ = metadata contracts
  • docs/ = governance, taxonomy, quality, compatibility

Rules for changes

  • Keep changes tightly scoped to the request.
  • Do not add secrets, credentials, tokens, tenant IDs, wallets, or customer data.
  • Prefer official docs and live evidence for cloud/compliance claims.
  • Treat destructive actions, broad permissions, and MCP mutation paths as high risk.
  • Update catalog metadata when adding, moving, or removing cataloged assets.
  • If intentional changes are made under cataloged skills/**, refresh the skill manifest with npm run manifest:write.
  • Run npm run validate before finishing.

Cross-platform asset rule

This repo supports multiple harnesses without pretending they are identical.

  • Keep portable logic in canonical/shared assets.
  • Keep harness-specific behavior in the correct adapter format.
  • Do not invent unsupported executable metadata fields.

Read these when relevant

  • README.md
  • AGENTS.md
  • docs/compatibility.md
  • docs/normalized-platform-matrix.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.