refactor(agent-policy): streamline instruction surfaces and eliminate dead content - #502
Merged
Conversation
… dead content - Remove 4 obsolete/conflicting agent personas (blueprint-mode, debug, janitor, software-engineer-agent-v1) - Remove 3 redundant/foreign skills (context-map, editorconfig, make-repo-contribution) - Condense github-actions, code-review, and context-engineering instruction surfaces - Update instruction-surfaces.json manifest accordingly
ss-o
added a commit
that referenced
this pull request
Aug 15, 2026
#503) refactor(agent-policy): streamline instruction surfaces and eliminate dead content (#502) * docs(adr): propose Zsh scripting standard * feat(zsh): add organization scripting standard * fix(zsh): harden scripting standard contract * fix(zsh): close semantic validation gaps * fix(zsh): pin canonical dispatcher integrity * fix(zsh): model startup files explicitly * fix(zsh): close startup policy review gaps * docs(zsh): reconcile standard consumers * fix(zsh): harden consumer lifecycle contracts * fix(zsh): close consumer validation gaps * fix(zsh): complete consumer contract parsing * fix(zsh): close markdown consumer bypasses * fix(zsh): preserve markdown block boundaries * fix(zsh): complete markdown block states * fix(zsh): enforce markdown leaf ownership * fix(zsh): respect markdown block interruptions * fix(zsh): preserve raw markdown ownership * fix(zsh): end leaf blocks at sibling containers * fix(zsh): preserve list html blank lines * chore(zsh): satisfy public verification checks * style(docs): preserve text conventions * refactor(agent-policy): streamline instruction surfaces and eliminate dead content - Remove 4 obsolete/conflicting agent personas (blueprint-mode, debug, janitor, software-engineer-agent-v1) - Remove 3 redundant/foreign skills (context-map, editorconfig, make-repo-contribution) - Condense github-actions, code-review, and context-engineering instruction surfaces - Update instruction-surfaces.json manifest accordingly * ci(workflows): install zsh in agent instruction validation workflow * test(agent-policy): update expected workflow fragments for zsh setup and next branch --------- Co-authored-by: Sal <ss-o@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.
Summary
Streamlines organization instruction surfaces to drastically reduce startup token bloat, eliminate contradictory authority prompts, and remove obsolete agent/skill artifacts.
blueprint-mode,software-engineer-agent-v1,debug, andjanitor.context-map,editorconfig, andmake-repo-contribution.github-actions-ci-cd-best-practices.instructions.md(reduced by 94% to concise, normative Z-Shell workflow conventions).code-review-generic.instructions.md(reduced by 85% to shell-dialect classification and lifecycle verification).context-engineering.instructions.md(reduced by 62% to multi-repo and dialect context guidance)..github/instruction-surfaces.jsonaccordingly.Verification
python3 scripts/validate-agent-policy.py(passed).python3 -m unittest scripts/test_validate_agent_policy.py(all 73 unit tests passed).