0.4.0#3
Merged
Merged
Conversation
Covers test commands, architecture fundamentals (rule structure, coordinates, capability model), key conventions (backbone.yml path resolution, changelog workflow, schema references), and interactive skills. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Phase 1 of Copilot contribution parity: - Created agents/copilot/config.yml with instruction file patterns - Updated backbone.yml to register copilot agent - Added copilot test fixture for CORE:S:0001 - Test harness now supports --agent copilot flag Copilot uses .github/copilot-instructions.md as main instruction file. Excludes CORE:S:0010 (AGENTS.md) and all CLAUDE:* rules. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Phase 2 of Copilot contribution parity: - Added workflow entry points for rule generation, implementation, validation - Added context-specific constraints for core rules, schemas, agent configs - All workflows reference .shared/ content (agent-agnostic) - Copilot now has same access to workflows as Claude, just different invocation Copilot users read instructions -> follow .shared/workflows/*.md Claude users invoke /skills -> .claude/skills/*.md -> .shared/workflows/*.md Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Phase 3 of Copilot contribution parity: - Updated README.md to list Copilot as supported agent - Updated CONTRIBUTING.md with agent-agnostic workflow guidance - Added copilot/rules/ to repository structure documentation - Clarified that Claude uses /skills, Copilot follows .shared/workflows/ Contributors can now use Claude Code, Codex, or Copilot CLI to work on rules. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The test runner was loading agent configs but ignoring the 'excludes' field. This caused copilot to run all 47 rules including 10 CLAUDE:* rules that should have been excluded. Changes: - load_agent_config() now returns (vars, excludes) tuple - Added rule_matches_exclude() to support wildcard patterns (CLAUDE:*) - discover_rules() now filters out excluded rules - Copilot now correctly tests 36 rules (30 CORE - 1 + 7 CODEX) Excludes support exact match and namespace wildcards: - Exact: CORE:S:0010 - Wildcard: CLAUDE:* (excludes all CLAUDE rules) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Previously, test runner scanned ALL agents/*/rules/ directories regardless of
which agent was being tested. This caused copilot to test 7 CODEX rules that
are specific to AGENTS.md, not copilot-instructions.md.
Changes:
- _scan_root() now accepts agent parameter
- When agent specified, only scans agents/{agent}/rules/ directory
- discover_rules() passes agent to _scan_root()
- Each agent now tests CORE + own agent-specific rules only
Rule counts:
- Copilot: 29 (30 CORE - 1 excluded + 0 COPILOT)
- Claude: 39 (30 CORE - 1 excluded + 10 CLAUDE)
- Codex: 37 (30 CORE + 7 CODEX)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
GitHub Copilot CLI now supports Agent Skills in .claude/skills/ directory, using the same format as Claude Code. This means Copilot can automatically invoke the existing skills without any additional setup. Changes: - Updated Skills section to show Copilot usage patterns - Clarified that .claude/skills/ works for both Claude and Copilot - Renamed section to 'Workflows (Manual Reference)' for fallback use - No new skills needed - existing .claude/skills/ works for both agents Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The repository was reorganized from 30 CORE rules down to 11 CORE rules. Updated copilot config to reflect current state: Changes: - Removed CORE:S:0010 from excludes (rule no longer exists) - Added CODEX:* to excludes (copilot shouldn't test CODEX rules) - Added skills_dir variable (Copilot CLI now supports Agent Skills) - Updated comment to reflect skills support Current rule counts: - 11 CORE rules (3 structure, 5 content, 1 governance, 2 maintenance) - 2 COPILOT rules - Total: 13 rules tested for copilot agent Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Massive rules reduction
Sharpening rules
Adding copilot support