Skip to content

KamiJeong/tech-bridge-book / .agents/skills/speckit-guards

speckit-guards

Verified

Guard scripts for Codex Spec Kit multi-agent workflow safety and token observability.

Spec Kit Guards

Scripts live in .agents/skills/speckit-guards/scripts/.

Scripts

  • guard-no-app-code-change.sh: verifies read-only phases did not modify application code outside allowed workflow artifact paths.
  • guard-before-implement.sh: blocks unsafe implementation when analyze, risk, tests, unrelated changes, or token-analyzer conditions fail.
  • guard-before-commit.sh: blocks unsafe commits when validation fails, unrelated changes exist, secrets are suspected, or token-analyzer is missing for auto-commit without approval.
  • guard-before-pr.sh: blocks unsafe PR creation on protected branches, missing GitHub CLI/authentication, unclear base branch, unrelated changes, or missing token-analyzer without approval.
  • guard-token-analyzer-available.sh: detects token-analyzer by extension directory, scripts, or command references and recommends installation when missing.
  • validate-agent-definitions.sh: rejects missing, malformed, incomplete, or mismatched .codex/agents/*.toml role definitions.
  • record-token-step.sh: writes per-phase token step JSON.
  • generate-token-report.sh: writes per-run summary, report, and quality notes.

Read-Only Boundary

Token analysis and guard checks must not mutate product artifacts. The only normal writes for token observability are under .specify/token-analysis/.

Usage

Run guards before protected actions and record their output in the validation evidence log for the active feature.

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall