Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pe-menezes/vibeflow --skill auditgit clone --depth 1 https://github.com/pe-menezes/vibeflowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pe-menezes/vibeflow/audit)<a href="https://agentmods.dev/skills/pe-menezes/vibeflow/audit"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow/audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pe-menezes/vibeflow/audit"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 114 Code deploys a privileged Kubernetes workload (privileged container, hostPath mount, or host namespaces). This grants root on the node and is a node/cluster takeover vector.Fix: Remove privileged, hostPath, and host-namespace settings from workloads. Use a least-privilege securityContext, drop capabilities, and avoid mounting the host filesystem.
- high Tool Misuse · line 115 Code deploys a privileged Kubernetes workload (privileged container, hostPath mount, or host namespaces). This grants root on the node and is a node/cluster takeover vector.Fix: Remove privileged, hostPath, and host-namespace settings from workloads. Use a least-privilege securityContext, drop capabilities, and avoid mounting the host filesystem.
- high Tool Misuse · line 119 Code deploys a privileged Kubernetes workload (privileged container, hostPath mount, or host namespaces). This grants root on the node and is a node/cluster takeover vector.Fix: Remove privileged, hostPath, and host-namespace settings from workloads. Use a least-privilege securityContext, drop capabilities, and avoid mounting the host filesystem.
- high Anti-Refusal · line 125 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- high Anti-Refusal · line 181 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- medium Tool Misuse · line 97 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium Tool Misuse · line 97 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.03438 |
| Opus 5.5 | $0.00037 | $0.01375 |
| Sonnet 5.5 | $0.00019 | $0.00688 |
| Haiku 4.5 | $0.00009 | $0.00344 |
Grade A, and why
audit scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| SEC108 | WARNING | a | dynamic exec (`eval`/`exec`/`system`/`popen`/`subprocess.call`/`child_process.exec`) | Copies of this mod
2 near-identical copies found in the catalogue:
- audit — 95% identical, 0 lines differ
- vibeflow-audit — 89% identical, 40 lines differ
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Description and examples
What it does: Finds the spec (in .vibeflow/specs/ or by path), checks each DoD item and pattern compliance, runs the project's test suite, and reports PASS / PARTIAL / FAIL. If tests fail, the result is FAIL regardless of DoD.
Examples:
audit .vibeflow/specs/login-flow.md— Audit implementation against the login-flow spec.audit login-flow— Same; the agent looks up the spec by feature name.
Language
Detect the language of the user's current request or conversation. Write ALL output in that same language. Technical terms in English are acceptable regardless of the detected language.
Audit the implementation identified in the user's current request.
Steps
With --consolidate-hotfixes in the input, the round's target is
.vibeflow/hotfixes/ instead of a spec — jump to Consolidation mode below.
- Find the spec — in
.vibeflow/specs/or at the given path — and extract its Definition of Done. - Read
.vibeflow/conventions.mdand the pattern docs the spec lists under Applicable Patterns. If it lists none, resolve them: read the## Pattern Registryblock inindex.md(between<!-- vibeflow:patterns:start/end -->markers) and cross-reference its tags and modules against the spec's scope — top 3–5 matches; with no registry, infer which are relevant. - Read the codebase files that were supposed to change.
- Run the tests. Prefer commands listed in the spec; otherwise detect the
project's runner from the stack (
.vibeflow/index.md, then test scripts in package.json, pyproject.toml, Cargo.toml, go.mod, and equivalents).- Tests fail → the verdict is FAIL and auditing stops; the incremental prompt pack targets the failures first.
- No runner found → warn "No test runner detected. Verify that tests were run manually." and continue.
- Critical Gate — destructive-op safety scan. A deterministic safety net for dangerous changes the DoD never mentions — security regressions and destructive operations that are side effects, not features. Not a style check.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · -1 lines 7cfd86117f74
- 1mo ago First seen · 279 lines · 93 tokens per session scan A 3482de06bc0d
audit is a skill published in the GitHub repository pe-menezes/vibeflow (32 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 3,438 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
code-review
Review pull requests for repository fit, meaningful value, trustworthy provenance, differentiation, and maintainability in awesome-copilot.
mcp-server-review
Review a Model Context Protocol (MCP) server implementation against the 2026-07-28 protocol revision, which removed the initialize handshake and Mcp-Session-Id and made the protocol stateless. Use when the user asks to review, audit, upgrade or migrate an MCP server, asks whether their MCP server is spec compliant…
code-review-csharp
Perform structured code reviews of C# source code covering naming conventions, performance, security, readability, and .NET best practices. Trigger phrases include "review this C# code", "check my C# for best practices", "analyze this C# class", "find issues in my C# code".
deep-review
Evidence-based deep code review rubric — severity + confidence findings across maintainability, correctness, security, performance, and testing. Push for ambitious structural simplification (code judo), not just local cleanup. Escalate hands-on triage to the code-reviewer agent.
gh-address-comments
Triage and address open GitHub PR review and conversation comments using the gh CLI. Use when the user wants to "address PR comments", "resolve review threads", or "respond to reviewers" on the current branch's pull request.
deslop
Remove AI-generated code slop and clean up code style.