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 agentmods add skills/reqvire-org/reqvire/auditnpx skills add reqvire-org/reqvire --skill auditgit clone --depth 1 https://github.com/reqvire-org/reqvireWhat 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 | $0.00077 | $0.00604 |
| Opus 5 | $0.00039 | $0.00302 |
| Sonnet 5 | $0.00015 | $0.00121 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade A, and why
reqvire-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- reqvire-audit — 88% identical, 8 lines differ
What it actually says
Reqvire Audit Skill
You are an expert Reqvire model auditor. You inspect, analyze, and report on model quality, coverage, lint issues, and change impact.
Environment Setup
Use the Reqvire npm runner by default:
npx -y "${REQVIRE_NPX_PACKAGE:-@reqvire-org/reqvire@latest}" --workspace "$PWD" <command>
Run from the intended effective workspace root, or pass that root with --workspace. The workspace must contain at least one eligible Git worktree; non-Git workspace folders are ignored by Reqvire model processing.
Reference Documents
- Analyze Model — comprehensive model structure analysis, validation, and recommendations
- Analyze Coverage — verification and implementation coverage gap analysis
- Change Impact — change propagation analysis using eligible Git worktree commit history
- Lint — lint, fix, and find redundant verify relations
When to Use Each Reference
| User intent | Reference |
|---|---|
| "analyze the model", "what's wrong", "model health" | AnalyzeModel |
| "coverage gaps", "unverified requirements", "what needs verification" | AnalyzeCoverage |
| "what changed", "impact of changes", "change impact" | ChangeImpact |
| "lint", "fix issues", "redundant verifications", "clean up" | Lint |
Quick Diagnostic Commands
# Full validation
npx -y "${REQVIRE_NPX_PACKAGE:-@reqvire-org/reqvire@latest}" --workspace "$PWD" validate --json --output /tmp/validation.json
# Coverage summary
npx -y "${REQVIRE_NPX_PACKAGE:-@reqvire-org/reqvire@latest}" --workspace "$PWD" coverage --json --output /tmp/coverage.json
# Lint check
npx -y "${REQVIRE_NPX_PACKAGE:-@reqvire-org/reqvire@latest}" --workspace "$PWD" lint --json --output /tmp/lint.json
# Auto-fix lint issues
npx -y "${REQVIRE_NPX_PACKAGE:-@reqvire-org/reqvire@latest}" --workspace "$PWD" lint --fix
Use /tmp for all JSON outputs.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 59 lines · 77 tokens per session scan A e19075b5f28c
reqvire-audit is a skill published in the GitHub repository reqvire-org/reqvire (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 604 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
context-generate
Assemble a context package (code graph, requirements, constraints, blast radius) before a downstream generation task runs - human-approved, source-attributed. Do NOT use for simple lookups.
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
change
Track and inspect graph changes, diffs, temporal updates, and the impact of new data on Semantica knowledge graphs.
coding
编写并运行 Python 代码，验证脚本逻辑和输出。.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
kayba-stage-6-hitl
Human-In-The-Loop gate that presents the action plan with full context, collects an informed approval/modification/rejection decision, and records the outcome. Trigger when the user says "run stage 6", "HITL review", "approve action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md…