Hyperflow Audit
Hyperflow code review. Use when the user wants the current diff, a commit, branch, or PR reviewed — verbs like audit, review, "check for issues", "security check", "code review". Multi-level review (L1 quick → L5 exhaustive), writes findings to .hyperflow/audits/, then a fix-gate.
Install
$ agentstack add skill-jeremylongshore-claude-code-plugins-plus-skills-hyperflow-audit ✓ 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.
About
hyperflow-audit — review phase (Antigravity single-agent)
Multi-level review over a target (default: git diff HEAD + staged). Follow the hyperflow doctrine. Security scan is mandatory at L3+.
Levels
| L | Checks | |---|--------| | 1 | syntax, obvious bugs, formatting | | 2 | L1 + spec compliance, naming, edge cases | | 3 | L2 + cross-file consistency, integration risks, security (secrets, injection, path traversal, XSS, missing validation) | | 4 | L3 + architecture, scalability, accessibility | | 5 | L4 + adversarial probing, perf profiling, alternatives |
Default to L2; elevate to L3 when the diff touches auth, data, money, or external input.
Steps
- Resolve scope (target arg or current diff). Read the changed files + their immediate dependencies.
- Review at the chosen level. Grade each finding
[Critical] / [Important] / [Suggestion] / [Praise]withfile:line+ a concrete fix. - Write the full report to
.hyperflow/audits/-.md(status table → TL;DR → findings → security-scan table). Print a one-line summary pointing at the file. - Fix gate via AskUserQuestion (only when Critical/Important exist):
Fix all (Recommended) / Critical+Important / Critical only / No. On a fix choice, route the findings intohyperflow-scope→hyperflow-dispatch. OnSECURITY_VIOLATION, skip the gate and surface immediately.
Rules
- Findings live in the file, not chat — chat shows only the summary box.
- A clean run (no Critical/Important) prints
Audit cleanand still writes the file for history.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jeremylongshore
- Source: jeremylongshore/claude-code-plugins-plus-skills
- License: MIT
- Homepage: https://tonsofskills.com
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.