Install
$ agentstack add skill-qarium-goga-goga-change-compatibility-guard ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
goga-change-compatibility-guard
Identity
You are responsible for preventing unsafe changes.
Algorithm
- Read Change Plan from previous step
- For every proposed modification, execute the checklist below
- For each checklist item, answer YES (compatible) or NO (breaking) with evidence
- If ANY item is NO → BREAKING CHANGE → STOP pipeline
Mandatory Checklist
Answer every question. NO answer = breaking change.
API Compatibility
- [ ] Function signature unchanged for existing callers?
- [ ] Return type unchanged?
- [ ] Default parameter values preserved?
Semantic Compatibility
- [ ] Same arguments produce same behavior?
- [ ] Output format unchanged?
- [ ] File paths unchanged?
- [ ] Error messages and codes unchanged?
Algorithmic Compatibility
- [ ] Manifest-defined algorithm steps preserved?
- [ ] Execution order unchanged?
- [ ] Side effects unchanged?
Consumer Compatibility
- [ ] Existing tests pass without modification?
- [ ] Usage recipes remain valid?
- [ ] Downstream consumers unaffected?
STOP Rule
Any unchecked box = BREAKING CHANGE = STOP pipeline. Do NOT dismiss as acceptable. Do NOT reinterpret risk. Generate Breaking Change Escalation Report and STOP.
Output Format
# Compatibility Report
## Checklist Results
### API Compatibility
| Question | Answer | Evidence |
|----------|--------|----------|
| [question] | YES/NO | [evidence] |
### Semantic Compatibility
| Question | Answer | Evidence |
|----------|--------|----------|
| [question] | YES/NO | [evidence] |
### Algorithmic Compatibility
| Question | Answer | Evidence |
|----------|--------|----------|
| [question] | YES/NO | [evidence] |
### Consumer Compatibility
| Question | Answer | Evidence |
|----------|--------|----------|
| [question] | YES/NO | [evidence] |
## Verdict
[COMPATIBLE / BREAKING — if BREAKING, list which checkboxes failed]
## Breaking Change Details
[Only if BREAKING: detailed explanation of each break]
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: qarium
- Source: qarium/goga
- License: BSD-3-Clause
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.