Skip to content

feat(protocols): recognize Deep Agents protocol skill activation - #35

Closed
sriaradhyula wants to merge 1 commit into
mainfrom
codex/scope-deepagents-protocol-skills
Closed

sriaradhyula wants to merge 1 commit into
mainfrom
codex/scope-deepagents-protocol-skills

Conversation

@sriaradhyula

Copy link
Copy Markdown

Deep Agents advertises released accord-/concord- skill names and loads instructions with read_file. The detector currently recognizes only legacy l9-* names and explicit activation/script tools, so actual skill loads remain invisible.

Keep legacy prefixes and accept released names. Count a successful read_file only when its exact /skills/.../SKILL.md path was advertised in the same agent's system catalog. Failed reads, another agent's catalog and unadvertised paths do not count. This proves instructions loaded, not script execution or protocol completion; script-level metric requirements remain unchanged.

Validation: all 52 cognition-protocols worker tests pass, including eight cases for both protocols covering successful/failed reads, missing catalogs and wrong-agent reads. Ruff E/F checks and diff checks pass. The matching CAIPE exporter sends only catalog metadata and matching file paths. A new worker image must be published/promoted before canary acceptance.

Prepared with Codex. Commits carry the human-provided Signed-off-by.

Signed-off-by: Sri Aradhyula <sraradhy@cisco.com>
@sriaradhyula
sriaradhyula requested a review from a team as a code owner November 17, 2026 00:01
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant