Vaultspec Code Review
Run a formal code review for safety, intent, and quality. Use to verify completed work before marking it done.
Install
$ agentstack add skill-nevenincs-vaultspec-core-vaultspec-code-review ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-nevenincs-vaultspec-core-vaultspec-code-review) 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
Code review skill (vaultspec-code-review)
When to use this skill:
- Mandatory: At the end of every
vaultspec-executecycle, before marking a feature
as "Done", and before publishing a PR.
- After major feature implementation work.
- When you need a second pair of eyes on a specific module or PR.
- Safety Check: When you suspect a safety violation (e.g.,
unsafeusage) or
testing framework issue in complex projects.
Workflow
- Announce at start: "I'm using the
vaultspec-code-reviewskill to audit the
implementation."
- Identify relevant docs, the plan (
.vault/plan/...), ADR and research documents
- Identify files modified
- Scaffold the audit document with
vaultspec-core vault add audit --feature {feature};
the CLI owns the filename and frontmatter. Log discovered issues to its body as triaged LOW->CRITICAL task entries.
- Use a
vaultspec-code-revieweragent persona, or other code-review specialists.
- Use parallel subagents to comprehensively comb through codebase.
- Instruct agents to always read grounding docs, ADRs, and plans.
- Instruct agents to log findings as triaged issue entries into the single shared
scaffolded audit document's body.
- Code review is not a code fixer skill - do NOT modify the codebase.
Important
- Template: You MUST read and use the template at
.vaultspec/templates/audit.md;
its embedded hint blocks govern the body structure, and its ## Findings section carries the rolling per-finding log format.
- Location: the scaffold creates
.vault/audit/yyyy-mm-dd-{feature}-audit.md; never
hand-write the filename or frontmatter. When the feature already carries an audit, disambiguate with the optional narrative infix: yyyy-mm-dd-{feature}-{topic}-audit.md.
- Tags: the scaffold tags the audit document with
#auditand#{feature}; verify
via vaultspec-core vault check all rather than hand-editing.
- Issues must be continuously appended to the audit document as a rolling log of open
tasks.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: nevenincs
- Source: nevenincs/vaultspec-core
- License: MIT
- Homepage: https://neve.md/vaultspec
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.