Add GitAgent Protocol support (agent.yaml + SOUL.md) - #6
Open
shreyas-lyzr wants to merge 1 commit into
Open
Conversation
Adds two files required by the GitAgent Protocol spec (https://gitagent.sh): - agent.yaml — standard manifest (name, version, model, skills, compliance) - SOUL.md — orchestrator persona distilled from CLAUDE.md Nothing else is modified.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Hi Paul! 👋
This PR proposes GitAgent Protocol (GAP) support for claude-code-agents — a small, open standard for portable AI agents at https://gitagent.sh.
What this adds (nothing else changes):
agent.yaml— a standard manifest encoding your orchestrator's name, version, preferred model (anthropic:claude-sonnet-4-6), your 6 workflow skills, runtime settings, and compliance tier (human_in_the_loop: destructive— requiring human confirmation before any destructive action)SOUL.md— your orchestrator's persona distilled fromCLAUDE.md: who it is, its 24-agent taxonomy, its constraints (single security authority, .env off-limits, mandatory status blocks), and how it's invokedWhy it might be useful:
human_in_the_loop: destructiveflag tells runtimes your agent requests confirmation on destructive ops — matching your existing design intentFeel free to tweak, close, or leave it open — it's purely a proposal. Thanks for building this in the open! 🦀