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 vibeflow-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/vibeflow-audit)<a href="https://agentmods.dev/skills/pe-menezes/vibeflow/vibeflow-audit"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow/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/vibeflow-audit"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow/vibeflow-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00086 | $0.03338 |
| Opus 5 | $0.00043 | $0.01669 |
| Sonnet 5 | $0.00017 | $0.00668 |
| Haiku 4.5 | $0.00009 | $0.00334 |
Grade A, and why
vibeflow-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 10d 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`) | This is a copy
89% identical to audit — 40 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibeflow: Audit
Audit recent work against its Definition of Done and project patterns.
Compares the current state of the code against the spec/DoD and verifies
the implementation follows conventions from .vibeflow/.
Usage: Provide the spec file path or feature name as input.
Language
Detect the language of the user's input. Write ALL output in that same language. Technical terms in English are acceptable regardless of the detected language.
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.
a. Compute the real diff (added vs removed lines — required, because the highest-value rules detect removed protections):
- Uncommitted work:
git diff HEAD - Committed on a branch:
git diff <base>...HEAD(base =main/master) b. Match each changed line against the Rules Catalog below. A rule fires only when the diff line's direction matches itsscope(a=added, r=removed, b=both) AND the file matches the rule's target types. c. Honor overrides. Skip a finding if the spec, the PR body, or a comment near the line containsvibeflow:allow <RULE_ID>: <reason>. CRITICAL/HIGH require a non-empty justification; WARNING/INFO may be overridden without one. d. Map findings to the verdict: | Unresolved finding | Effect | |---|---| | CRITICAL / HIGH | FAIL — listed first in the incremental prompt pack | | WARNING | caps the verdict at PARTIAL; listed, does not block | | INFO | informational note only | | none | proceed normally |
- Uncommitted work:
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.
- 10d ago First seen · 264 lines · 86 tokens per session scan A fc41761af4ba
vibeflow-audit is a skill published in the GitHub repository pe-menezes/vibeflow (29 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 3,338 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). It is 89% identical to audit, differing in 40 lines, and is treated as a copy.
Other skills, from other repositories
gentle-ai-bench
Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
phoenix-review
Review completed work against the Intent Contract's acceptance criteria using objective evidence, not opinion — re-run every check, confirm no regressions, inspect the tamper-evident trace, and surface only real issues (bugs, unmet criteria, regressions). Use before shipping, after a feature is built, or when the user…
verify-against-rubric
Spawn a stateless sub-agent (Claude Code Task tool, Cursor agent mode, or equivalent) with ONLY the artifact path plus the locked rubric plus read-only tools. Sub-agent returns a structured verdict (satisfied, needsrevision, or failed) plus per-criterion feedback. Distinct from self-critique-and-revise (same-context…
pr-coverage-reviewer
Use when the parent pipeline routes a coverage-related PR review request. Reads the diff and emits structured coverageFindings using the coverage specialist heuristics.
ndv-temporal
Trajectory-aware cognitive module. Injects lifecycle and direction-of-change thinking into architecture reviews, dependency audits, and technology selection — where direction matters as much as current state. Emergent.