Agent skill
push
Test, commit, and push in one atomic workflow. Runs Go and Python tests, commits with conventional message, pushes to current branch.
Install this agent skill to your Project
npx add-skill https://github.com/boshu2/agentops/tree/main/skills-codex/push
SKILL.md
Push Skill
Atomic test-commit-push workflow. Catches failures before they reach the remote.
Steps
Step 1: Detect Project Type
Determine which test suites apply:
- Go: Check for
go.mod(orcli/go.mod). If found, Go tests apply. - Python: Check for
requirements.txt,pyproject.toml, orsetup.py. If found, Python tests apply. - Shell: Check for modified
.shfiles. If found, shellcheck applies (if installed).
Step 2: Run Tests
Run ALL applicable test suites. Do NOT skip any.
Go projects:
cd cli && go vet ./...
cd cli && go test ./... -count=1 -short
Python projects:
python -m pytest --tb=short -q
Shell scripts (if shellcheck available):
shellcheck <modified .sh files>
If ANY test fails: STOP. Fix the failures before continuing. Do not commit broken code.
Step 3: Stage Changes
git add <specific files>
Stage only the files relevant to the current work. Do NOT use git add -A unless the user explicitly requests it. Review untracked files and skip anything that looks like secrets, temp files, or build artifacts.
Step 4: Write Commit Message
Write a conventional commit message based on the diff:
- Use conventional commit format:
type(scope): description - Types:
feat,fix,refactor,docs,test,chore,style,perf - Keep subject line under 72 characters
- Focus on WHY, not WHAT
Step 5: Commit
git commit -m "<message>"
Step 6: Sync with Remote
git pull --rebase origin $(git branch --show-current)
If rebase conflicts occur: resolve them, re-run tests, then continue.
Step 7: Push
git push origin $(git branch --show-current)
Step 8: Report
Output a summary:
- Files changed count
- Tests passed (with suite names)
- Commit hash
- Branch pushed to
Guardrails
- NEVER push to
mainormasterwithout explicit user confirmation - NEVER stage files matching:
.env*,*credentials*,*secret*,*.key,*.pem - If tests were not run (no test suite found), WARN the user before committing
- If
git pull --rebasefails, do NOT force push — ask the user - Do NOT run
ao codex stopafter the remote push. If session closeout is needed, finish it through$validation,$post-mortem, or$handoffbefore entering$push
Local Resources
scripts/
scripts/validate.sh
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
swarm
Spawn isolated Codex sub-agents for parallel task execution using the current runtime primitives. Triggers: "swarm", "spawn agents", "parallel work", "run in parallel", "parallel execution".
council
Multi-perspective review for Codex using the current sub-agent runtime. Triggers: "council", "get consensus", "multi-model review", "multi-perspective review", "council validate", "council brainstorm", "council research".
openai-docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.
crank
Hands-free epic execution for Codex using wave-based sub-agents and lead-side validation. Triggers: "crank", "run epic", "execute epic", "run all tasks", "hands-free execution", "crank it".
pr-retro
Learn from PR outcomes. Analyzes accept/reject patterns and updates contribution lessons. Triggers: "pr retro", "learn from PR", "PR outcome", "why was PR rejected", "analyze PR feedback".
ratchet
Brownian Ratchet progress gates for RPI workflow. Check, record, verify. Triggers: "check gate", "verify progress", "ratchet status".
Didn't find tool you were looking for?