Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Config Guardian · sundial-org | DecimalAI

agent toolingby sundial-org

Config Guardian

sundial-org/config-guardian

Source sundial-org/awesome-openclaw-skills ↗License Not recorded

Validate and safeguard OpenClaw config updates (openclaw.json or openclaw config set/apply).

SkillScore82Maintained

Automatic

DevOps & SRE pack

Last verified 8/19/2026

What it changes

Passed 16 of 20 test cases with the skill, and 5 of 20 without it.

Without skill27%

With skill82%

Checks it passed that the model alone missed

Uses scripts/backup_config.sh before starting direct file edits.
Uses scripts/restore_config.sh to execute the restore operation.
Requires confirming the requested change scope during preflight.

and 14 more in the full report

12 fixed6 passed either way4 still failing0 broke

Pass-rate lift: +55 pp
Tokens: -13%
Agent turns: 0%
Response time: -42%

Model gemini-3.6-flashMeasured 8/19/2026v118 of 22 cases passed with skill · 20 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/sundial-org-config-guardian/SKILL.md https://app.decimal.ai/s/sundial-org-config-guardian/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add sundial-org-config-guardian, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/sundial-org-config-guardian/ and pins it in .decimal/skills.lock

decimalai skills add sundial-org-config-guardian

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/sundial-org-config-guardian/SKILL.md https://app.decimal.ai/s/sundial-org-config-guardian/SKILL.md

Raw file: /s/sundial-org-config-guardian/SKILL.md ↗ · machine-readable summary at /s/sundial-org-config-guardian.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

What's inside

The instructions your model reads when the skill loads.

SKILL.md46 lines5 filesincludes scripts

Config Guardian

Overview

Use this workflow whenever editing ~/.openclaw/openclaw.json or running openclaw config set/apply. It prevents invalid config, creates backups, validates against schema, and enables rollback.

Workflow (use every time)

Preflight
- Confirm the requested change and scope.
- Check for sensitive keys (tokens, credentials).
Backup
- Run scripts/backup_config.sh to create a timestamped snapshot.
Validate (before change)
- Run scripts/validate_config.sh.
- If validation fails, stop and report.
Apply change
- Prefer openclaw config set <path> <value> for small changes.
- For complex edits, edit the file directly and keep diffs minimal.
Validate (after change)
- Run scripts/validate_config.sh again.
- If it fails, restore from backup with scripts/restore_config.sh.
Restart (only with explicit approval)
- If change requires restart, ask for approval first.
- Use openclaw gateway restart.

Guardrails

Never restart or apply config without explicit user approval.
Never remove keys or reorder blocks unless requested.
Always keep a backup before edits.
If unsure about schema: run openclaw doctor --non-interactive and stop on errors.

Scripts

scripts/backup_config.sh — create timestamped backup
scripts/validate_config.sh — validate config via OpenClaw doctor
scripts/diff_config.sh — diff current config vs backup

Track record

Benchmark

16 / 20

test cases passed, vs 5 / 20 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

sundial-org / awesome-openclaw-skills

skills/config-guardian/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1Bundled 4 files · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

What's inside

Config Guardian

Overview

Workflow (use every time)

Guardrails

Scripts

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills