DCG: When You Get Blocked

SkillDatabases & data

Handle blocked destructive commands. Use when dcg blocks rm -rf, git reset --hard, DROP DATABASE, kubectl delete, or when configuring agent safety guardrails.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the DCG: When You Get Blocked skill

What this skill tells your AI

The instructions your AI receives, as published by dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations in skills/dcg/SKILL.md and read by ahel’s review.

Core Insight: Blocks are checkpoints, not errors. A safe alternative almost always exists. Find it before mentioning override.

Quick Navigation

I need to...Go to
Handle a block right nowTHE EXACT WORKFLOW
Find a safe alternativeSafe Alternatives
See all CLI commandsCOMMANDS.md
Enable more rule packsPACKS.md
Configure per-projectCONFIG.md
Debug hook issuesTROUBLESHOOTING.md

THE EXACT WORKFLOW

When blocked, follow this sequence every time:

1. Run `dcg explain "cmd"` → Understand why (see trace)
2. Check Safe Alternatives table → Use if exists (DON'T mention override)
3. No alternative? → Explain risk clearly, let human decide
4. Human approves? → THEY run: dcg allow-once CODE

Never: Ask for override first. Never retry silently. Never circumvent.

Example block output:

BLOCKED: git reset --hard HEAD
Rule: core.git:reset-hard
Reason: Discards uncommitted changes permanently
Allow-once code: ab12
Safer alternative: git stash

Good response:

"I wanted to discard changes but git reset --hard was blocked. Let me use git stash instead—recoverable if needed." [proceeds with stash]

Safe Alternatives

BlockedUse InsteadWhy
git reset --hardgit stashRecoverable
git checkout -- filegit stash push filePreserves changes
git push --forcegit push --force-with-leaseChecks remote unchanged
git clean -fdgit clean -fdn (preview)Shows what would delete
git stash dropgit stash list firstVerify which stash
rm -rf /pathrm -ri /path or verify pathInteractive/confirm
kubectl delete namespacekubectl delete -l app=XSelective deletion
DROP DATABASEBackup firstHuman approves
docker system prune -adocker system df firstSee what's used

Quick Reference

dcg doctor              # Health check — hook registered?
dcg explain "cmd"       # WHY is it blocked? (with trace)
dcg test "cmd"          # Would this be blocked? (dry-run)
dcg allow-once CODE     # Human approves (THEY run this)
dcg packs               # List available rule packs
dcg scan --staged       # Pre-commit: scan for issues

What Gets Blocked

CategoryPatternsSafe Variants
Git destructivereset --hard, checkout --stash, restore --staged
Git historypush --force, branch -D--force-with-lease, -d
Git stashstash drop, stash clearstash list first
Filesystemrm -rf (dangerous paths)/tmp/* allowed
DatabaseDROP, TRUNCATE, DELETE w/o WHEREAdd WHERE clause
K8sdelete namespace, delete --all-l label selector

Context-aware: rm -rf ./build allowed, rm -rf / blocked.

dcg explain example (7-step pipeline):

$ dcg explain "git reset --hard HEAD"
BLOCKED by core.git:reset-hard

Evaluation trace:
  1. Config allow overrides: no match
  2. Config block overrides: no match
  3. Heredoc detection: not applicable
  4. Quick reject: triggered (contains "reset")
  5. Context sanitization: no changes
  6. Normalization: git reset --hard HEAD
  7. Pack evaluation:
     - Safe patterns: no match
     - Destructive: MATCH "reset --hard"

Suggestion: Use `git stash` to preserve changes

Anti-Patterns

❌ "Command blocked. Run dcg allow-once ab12"  → Find alternative first!
❌ *Retrying silently or circumventing*         → Always acknowledge blocks
❌ Treating blocks as errors                    → They're checkpoints
❌ Asking user to allow-once without explaining → They need context

Configuration

# .dcg.toml — enable rule packs per-project
[packs]
enabled = ["database.postgresql", "kubernetes.kubectl", "cloud.aws"]

[overrides]
allow_patterns = ["rm -rf ./node_modules"]  # Project-specific safe

Environment variables:

  • DCG_PACKS="containers.docker,kubernetes" — Enable packs
  • DCG_DISABLE="kubernetes.helm" — Disable specific packs
  • DCG_BYPASS=1 — Escape hatch (human-only)

Key Facts

  • 49+ rule packs available (database, containers, k8s, cloud, etc.)
  • Sub-millisecond latency — won't slow your workflow
  • Fail-open on timeout — if DCG hangs, command runs (with warning)
  • Heredoc scanning — inline scripts (bash -c, python -c) are analyzed
  • Allow-once codes — 4 hex chars, 24h expiry, bound to exact command+directory

The Incident That Started It All

On December 17, 2025, an AI agent ran git checkout -- on files containing hours of uncommitted work. The files were recovered via git fsck --lost-found, but it proved: instructions don't prevent execution—mechanical enforcement does.


Validation

# Quick health check
dcg doctor | head -20

# Test if a command would be blocked
dcg test "git reset --hard HEAD"

# Should show: WOULD BE BLOCKED

Scripts

ScriptUsage
./scripts/validate-dcg.shFull installation validation

References

Signals

GitHub stars
73
Forks
16
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
dcg-dicklesworthstone
Source
github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations