feat: add operating fundamentals for pure orchestration - #10
Merged
Conversation
Owner
Author
|
I reviewed the complete current diff, including the new 55-line skill, its focused contract test, and the X-mode/doc ownership integration. The frontmatter is valid and agent-only, the description names concrete intake/supervision/verification triggers, and all seven fundamentals are principle-level rather than incident- or provider-specific. In particular, shared validation is decoupled from an exhaustible worker budget without preferring a provider. The X-mode and documentation edits replace duplicated lifecycle wording with ownership pointers to the new contract; they do not introduce a separate concern. Verdict: ready. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Intent
Crystallize firstmate's durable operating fundamentals from the supplied recovery source into one concise agent-only skill, stripped of incident-specific provider, account, tool, crew, and task details. Encode seven principles: remain a pure orchestrator by turning every captain ask into both a durable backlog item and tracked crew assignment and never doing project or deliverable work inline; saturate available lanes; route around blockers; decouple shared validation from worker budgets; reap completed resources continuously; obey explicit captain orders within non-overridable constraints; and verify before asserting. Keep SKILL.md at or below 90 lines with concrete triggering situations in folded metadata, wire only a single conditional load trigger into AGENTS.md section 13, add no new every-turn inline rule because AGENTS.md section 1 already carries the always-loaded delegation contract and size and one-owner discipline matter, do not add maintenance boilerplate, and make no unrelated edits.
What Changed
Risk Assessment
✅ Low: Captain, the narrowly scoped documentation change cleanly encodes all seven required principles in a 55-line internal skill, adds only the required Section 13 trigger, and introduces no material source risk.
Testing
The full configured baseline was already green, and the new focused test plus manual loader, routing, content, size, and diff-scope checks all passed. This is an agent-only Markdown instruction surface with no rendered UI, so direct CLI evidence was captured instead of a screenshot.
Evidence: End-to-end skill loader, routing, principles, scope, and focused-test evidence
Pipeline
Updates from git push no-mistakes
✅ **intent** - passed
✅ No issues found.
✅ **Rebase** - passed
✅ No issues found.
✅ **Review** - passed
✅ No issues found.
✅ **Test** - passed
✅ No issues found.
command -v tmux >/dev/null || { echo "tmux is required for e2e tests" >&2; exit 1; }; tmux -V; rc=0; for t in tests/*.test.sh; do echo "== $t =="; bash "$t" || rc=1; done; uv run --directory tools/agent-fleet --locked pytest || rc=1; uv run --directory tools/agent-fleet --locked python -m compileall -q src || rc=1; exit "$rc"Configured baseline (already completed successfully):command -v tmux >/dev/null || { echo "tmux is required for e2e tests" >&2; exit 1; }; tmux -V; rc=0; for t in tests/*.test.sh; do echo "== $t =="; bash "$t" || rc=1; done; uv run --directory tools/agent-fleet --locked pytest || rc=1; uv run --directory tools/agent-fleet --locked python -m compileall -q src || rc=1; exit "$rc"Focused regression:bash tests/operating-fundamentals.test.shParsed loader metadata:ruby -ryaml -e '...' .agents/skills/operating-fundamentals/SKILL.mdVerified routing and scope with section-13 extraction, the 55/90 line count, seven ordered headings, andgit diff --name-status b4b16035a074e92eb0ac816149635f7d35d7a99d..d85d2ca89d11eea88b5f3c5ee8b8b13bb3e49048Captured and read back/var/folders/y_/bfdbj_vx20l9b9tw7crgkzwm0000gn/T/no-mistakes-evidence/01KY3E57H7YWH78RCWQNSE6WB1/operating-fundamentals-e2e.txt✅ **Document** - passed
✅ No issues found.
🔧 **Lint** - 1 issue found → auto-fixed ✅
🔧 Fix: Fix ShellCheck literal quoting warnings
✅ Re-checked - no issues remain.
✅ **Push** - passed
✅ No issues found.