KamiJeong/tech-bridge-book / .agents/skills/speckit-guards
speckit-guards
VerifiedGuard scripts for Codex Spec Kit multi-agent workflow safety and token observability.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.7 KB |
| scripts/generate-token-report.shexecutable | script | 5.9 KB |
| scripts/guard-before-commit.shexecutable | script | 1.0 KB |
| scripts/guard-before-implement.shexecutable | script | 1.3 KB |
| scripts/guard-before-pr.shexecutable | script | 1007 B |
| scripts/guard-no-app-code-change.shexecutable | script | 737 B |
| scripts/guard-token-analyzer-available.shexecutable | script | 1.4 KB |
| scripts/record-token-step.shexecutable | script | 4.4 KB |
| scripts/validate-agent-definitions.shexecutable | script | 3.7 KB |
scripts/guard-token-analyzer-available.sh
View on GitHub#!/usr/bin/env bash
set -euo pipefail
MODE="gated"
ALLOW_MISSING="false"
while [[ $# -gt 0 ]]; do
case "$1" in
--mode) MODE="${2:-gated}"; shift 2 ;;
--allow-missing) ALLOW_MISSING="true"; shift ;;
-h|--help)
echo "Usage: $0 [--mode plan-only|gated|auto-implement|auto-pr] [--allow-missing]"
exit 0
;;
*) echo "Unknown argument: $1" >&2; exit 2 ;;
esac
done
found="false"
reason=""
if [[ -d ".specify/extensions/token-analyzer" ]]; then
found="true"
reason=".specify/extensions/token-analyzer/ exists"
elif compgen -G ".specify/extensions/token-analyzer/scripts/*/*token*.sh" >/dev/null; then
found="true"
reason="token-analyzer scripts are available"
elif rg -q "token-analyzer" .specify .agents 2>/dev/null; then
found="true"
reason="token-analyzer command references are available"
fi
if [[ "$found" == "true" ]]; then
echo "PASS: token-analyzer available (${reason})"
exit 0
fi
echo "WARNING: token-analyzer is not available. Install with: specify extension add token-analyzer" >&2
case "$MODE" in
auto-implement|auto-pr|auto-commit)
if [[ "$ALLOW_MISSING" == "true" ]]; then
echo "WARNING: continuing without token-analyzer because explicit approval was provided" >&2
exit 0
fi
echo "FAIL: ${MODE} requires explicit approval before continuing without token-analyzer" >&2
exit 1
;;
*)
exit 0
;;
esac
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |