JetXu-LLMJetXu-LLM/DocMason/.github/copilot-instructions.md

DocMason

Copilot instructions152 starsChanged 4 months agoApache-2.0View on GitHub

Start by reading AGENTS.md. AGENTS.md is the baseline repository contract. This file is only the minimal GitHub Copilot adaptation layer for the current workspace. For an ordinary user request in GitHub Copilot: For explicit operator work:

Where files are headingNew Copilot instructions files have more rules about branches and pull requests, and fewer about code style.
Of the Copilot instructions files we read, the 2,349 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- adapter-syncSkill
- askSkill
- grounded-answerSkill
- grounded-compositionSkill
- knowledge-base-syncSkill
- knowledge-constructionSkill
- provenance-traceSkill
- retrieval-workflowSkill
- runtime-log-reviewSkill
- validation-repairSkill
- workspace-bootstrapSkill
- workspace-doctorSkill
- workspace-statusSkill
- operator-evalSkill
- public-sample-workspaceSkill

The file

Show its rules and text

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

14 rules. About 0 are common, 9 are distinctive, and 5 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Start by reading AGENTS.md.
line 3
Very specific:
after AGENTS.md, the normal next read is skills/canonical/ask/SKILL.md
line 9
Very specific:
do not start with workspace-status, workspace-bootstrap, source search, CLI help, or ad hoc implementation reading unless the request is …
line 11
Very specific:
do not treat direct retrieve or trace output as completion of the ask contract
line 12
Very specific:
follow the matching canonical workflow or stable docmason CLI from AGENTS.md
line 16
Distinctive:
do not force setup, status, sync, or review work through the ordinary ask front door
line 17
Distinctive:
Do not assume Codex-native behavior is available just because repository guidance mentions Codex as the native reference path.
line 21
Distinctive:
Use the current GitHub Copilot tool surface to achieve the same repository outcome when the exact Codex interaction model is different.
line 22
Very specific:
If a Codex-oriented note assumes implicit image visibility, use explicit image inspection tools such as view_image, or use published …
line 23
Distinctive:
Treat differences in transcript fidelity, attachment capture, or image visibility as current adapter-surface differences unless the …
line 24
Distinctive:
If a Codex-oriented workflow mentions main and sub agents, keep the main agent responsible for critical-path reasoning, mutations, …
line 25
Distinctive:
Prefer equivalent file reads, searches, validation surfaces, terminal commands, and published artifact inspection over inventing …
line 26
Distinctive:
Do not assume Claude-specific helpers, generated skill shims, or interaction-history enrichments are loaded unless the current GitHub …
line 27
Distinctive:
Keep the adaptation minimal.
line 28

≈ “Common” is an estimate: at least 1 in 5 of the 3,779 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

DocMason GitHub Copilot Notes

Start by reading AGENTS.md. AGENTS.md is the baseline repository contract. This file is only the minimal GitHub Copilot adaptation layer for the current workspace.

For an ordinary user request in GitHub Copilot:

after AGENTS.md, the normal next read is skills/canonical/ask/SKILL.md
then open canonical ask through the Canonical Ask Contract in that skill and follow the returned route
do not start with workspace-status, workspace-bootstrap, source search, CLI help, or ad hoc implementation reading unless the request is clearly explicit operator work or canonical ask returns that route
do not treat direct retrieve or trace output as completion of the ask contract

For explicit operator work:

follow the matching canonical workflow or stable docmason CLI from AGENTS.md
do not force setup, status, sync, or review work through the ordinary ask front door

Copilot-Specific Delta

Do not assume Codex-native behavior is available just because repository guidance mentions Codex as the native reference path.
Use the current GitHub Copilot tool surface to achieve the same repository outcome when the exact Codex interaction model is different.
If a Codex-oriented note assumes implicit image visibility, use explicit image inspection tools such as view_image, or use published multimodal artifacts such as visual_layout and render-linked evidence instead of assuming that file paths are already visually available.
Treat differences in transcript fidelity, attachment capture, or image visibility as current adapter-surface differences unless the repository explicitly states a product limitation.
If a Codex-oriented workflow mentions main and sub agents, keep the main agent responsible for critical-path reasoning, mutations, publication, and final sign-off. Use a subagent only when the current environment explicitly supports it and the delegated work is read-only or clearly disjoint.
Prefer equivalent file reads, searches, validation surfaces, terminal commands, and published artifact inspection over inventing Copilot-only behavior.
Do not assume Claude-specific helpers, generated skill shims, or interaction-history enrichments are loaded unless the current GitHub Copilot environment explicitly exposes them.
Keep the adaptation minimal. Do not create a parallel GitHub Copilot product contract when the existing repository contract already applies.

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.

Check your setup, free