AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Vaultspec Code Research

skill-nevenincs-vaultspec-core-vaultspec-code-research · by nevenincs

Ground a coding task in real source code, reference implementations, and library docs. Use before implementing a complex feature or when documentation is thin.

No reviews yet
0 installs
32 views
0.0% view→install

Install

$ agentstack add skill-nevenincs-vaultspec-core-vaultspec-code-research

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-nevenincs-vaultspec-core-vaultspec-code-research)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Vaultspec Code Research? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Code research skill (vaultspec-code-research)

Use this skill:

  • When auditing, researching, or implementing a specific technical implementation.
  • When you need to identify a reference project.
  • When you need source references that show how another project implements a feature.
  • To avoid missing implementation details.
  • To ground and de-risk complex coding tasks with actual code.

Invoke when the vaultspec-research -> vaultspec-adr -> vaultspec-write flow explicitly requires direct code referencing.

Announce at start: "I'm using the vaultspec-code-research skill to find out how {Reference} implements {Feature}."

Required steps

  • Ground in existing intent first. Lead the code deep dive with semantic search:

vaultspec-rag search "" --type code locates the semantically matching implementation sites - read the epicenter or nearest analogue in full, then confirm exact symbols with a targeted grep, which is sharper at exact-symbol lookup. Retrieve the governing decisions with vaultspec-rag search "" --type vault --doc-type adr (the directed ADR filter, sharper than catch-all --type vault) to anchor the audit. Where vaultspec-rag is not installed, the vaultspec-core discovery verbs and grep carry the same sequence.

  • Read and use the template at .vaultspec/templates/reference.md; its embedded

hint blocks govern the body structure.

  • Load the vaultspec-reference-auditor agent persona for the focused code deep

dives. Instruct it to locate and audit the {Feature} implementation in the reference codebase; it returns its findings to you for persistence.

  • Persist findings: scaffold the reference document with

vaultspec-core vault add reference --feature {feature}, then author the findings as body prose. The CLI owns the filename (.vault/reference/yyyy-mm-dd-{feature}-reference.md) and the frontmatter; never hand-write either. The full frontmatter schema is defined in the vaultspec rule; verify after scaffolding with vaultspec-core vault check all rather than hand-editing frontmatter.

Research and audit

Perform focused code deep dives.

Coordinate the loaded persona and any supporting agents to:

  • Locate the code snippets and files.
  • Analyze implementation patterns and architecture.
  • Persist a Reference blueprint into the scaffolded document's body. If the document

exists already, assess and update its body prose.

Implementation plan

You MUST check if an implementation exists already. If it does:

  • Do our findings alter the implementation? If so, report back to the user.
  • Report possible issues or drift and leave notes in the Plan that reference the

{Feature} audit.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.