terminal-ops
affaan-m/everything-claude-code
Evidence-first terminal execution workflow for debugging, testing, and pushing verified fixes.
What is terminal-ops?
Terminal Ops is a narrowly-scoped operator workflow for real repo execution tasks: running commands, inspecting git state, debugging CI failures, and making verified local fixes. Use it when the user needs exact proof of what was executed, tested, and changed before committing or pushing.
- Execute commands and capture exact output for debugging and verification
- Inspect repo state, git diffs, and test failures before making changes
- Keep fixes narrow and solve one dominant failure at a time
- Report precise execution status: inspected, changed locally, verified locally, committed, or pushed
- Integrate with ECC skills (verification-loop, tdd-workflow, security-review, github-ops, knowledge-ops) when relevant
- Distinguish between local changes, local verification, commits, and upstream pushes
How to install terminal-ops
npx skills add https://github.com/affaan-m/everything-claude-code --skill terminal-opsHow to use terminal-ops
- 1.Resolve the working surface: confirm repo path, branch, local diff state, and requested mode (inspect/fix/verify/push)
- 2.Read the failing surface first: inspect the error, relevant files, git state, and any supplied logs before making changes
- 3.Keep the fix narrow: use the smallest proving command first, solve one dominant failure at a time, and avoid broad retries
- 4.Execute the fix or verification command and capture exact output
- 5.Report execution status using precise words: inspected, changed locally, verified locally, committed, or pushed
Use cases
- Debug a failing CI build by running the exact command locally and inspecting the error
- Make a narrow fix to a single file, verify it with a minimal test, then push with proof
- Audit repo state and git history without making changes
- Investigate a test failure by running the failing test, inspecting the code, then applying a fix
- Push a verified commit upstream only after the proving command has been rerun successfully
- Developers debugging CI failures or test regressions
- Engineers making targeted fixes with verification requirements
- Teams needing audit trails of what was executed and verified
- Operators pushing changes with exact proof of local verification
terminal-ops FAQ
Use Terminal Ops when the user explicitly asks to run commands, debug CI, check the repo, fix something, or push changes—and when the answer must include exact proof of what was executed and verified.
It means inspecting the live repo state and error output before editing, running the proving command after any fix, and reporting exact status (inspected, verified locally, committed, pushed) rather than claiming success without proof.
No. Terminal Ops is intentionally narrow. Solve one dominant failure at a time, use the smallest proving command first, and avoid widening a fix into repo-wide churn.
Stop broad retries and narrow the scope. Inspect the error more carefully, check the file or test directly, and use a smaller or more targeted proving command.
Pull in verification-loop for proving steps, tdd-workflow for regression coverage, security-review for auth/secrets, github-ops for CI/PR state, and knowledge-ops to capture verified outcomes into project context.
Full instructions (SKILL.md)
Source of truth, from affaan-m/everything-claude-code.
name: terminal-ops description: Evidence-first repo execution workflow for ECC. Use when the user wants a command run, a repo checked, a CI failure debugged, or a narrow fix pushed with exact proof of what was executed and verified. metadata: origin: ECC
Terminal Ops
Use this when the user wants real repo execution: run commands, inspect git state, debug CI or builds, make a narrow fix, and report exactly what changed and what was verified.
This skill is intentionally narrower than general coding guidance. It is an operator workflow for evidence-first terminal execution.
Skill Stack
Pull these ECC-native skills into the workflow when relevant:
verification-loopfor exact proving steps after changestdd-workflowwhen the right fix needs regression coveragesecurity-reviewwhen secrets, auth, or external inputs are involvedgithub-opswhen the task depends on CI runs, PR state, or release statusknowledge-opswhen the verified outcome needs to be captured into durable project context
When to Use
- user says "fix", "debug", "run this", "check the repo", or "push it"
- the task depends on command output, git state, test results, or a verified local fix
- the answer must distinguish changed locally, verified locally, committed, and pushed
Guardrails
- inspect before editing
- stay read-only if the user asked for audit/review only
- prefer repo-local scripts and helpers over improvised ad hoc wrappers
- do not claim fixed until the proving command was rerun
- do not claim pushed unless the branch actually moved upstream
Workflow
1. Resolve the working surface
Settle:
- exact repo path
- branch
- local diff state
- requested mode:
- inspect
- fix
- verify
- push
2. Read the failing surface first
Before changing anything:
- inspect the error
- inspect the file or test
- inspect git state
- use any already-supplied logs or context before re-reading blindly
3. Keep the fix narrow
Solve one dominant failure at a time:
- use the smallest useful proving command first
- only escalate to a bigger build/test pass after the local failure is addressed
- if a command keeps failing with the same signature, stop broad retries and narrow scope
4. Report exact execution state
Use exact status words:
- inspected
- changed locally
- verified locally
- committed
- pushed
- blocked
Output Format
SURFACE
- repo
- branch
- requested mode
EVIDENCE
- failing command / diff / test
ACTION
- what changed
STATUS
- inspected / changed locally / verified locally / committed / pushed / blocked
Pitfalls
- do not work from stale memory when the live repo state can be read
- do not widen a narrow fix into repo-wide churn
- do not use destructive git commands
- do not ignore unrelated local work
Verification
- the response names the proving command or test
- git-related work names the repo path and branch
- any push claim includes the target branch and exact result
Related skills
More from affaan-m/everything-claude-code and the wider catalog.

security-review
Security checklist and patterns for authentication, input validation, secrets, and sensitive features.

golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable applications.

coding-standards
Baseline coding conventions for naming, readability, immutability, and quality across projects.

frontend-patterns
React and Next.js patterns for components, state management, performance, and modern frontend practices.

backend-patterns
REST/GraphQL API design, database optimization, and server-side patterns for Node.js, Express, and Next.js.

golang-testing
Go testing patterns: table-driven tests, subtests, benchmarks, fuzzing, and TDD methodology.