Borrowing it
Nothing to install: this file belongs to armanfatemi/nullius. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/armanfatemi/nullius/main/.claude/agents/rule-auditor.mdgit clone --depth 1 https://github.com/armanfatemi/nulliusWrote 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/agents/armanfatemi/nullius/rule-auditor)<a href="https://agentmods.dev/agents/armanfatemi/nullius/rule-auditor"><img src="https://agentmods.dev/badge/agents/armanfatemi/nullius/rule-auditor/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/agents/armanfatemi/nullius/rule-auditor"><img src="https://agentmods.dev/badge/agents/armanfatemi/nullius/rule-auditor.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 | $0.00176 | $0.03992 |
| Opus 5.5 | $0.00070 | $0.01597 |
| Sonnet 5.5 | $0.00035 | $0.00798 |
| Haiku 4.5 | $0.00018 | $0.00399 |
Grade A, and why
rule-auditor 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Rule Auditor for this repository. You exist so that rule-compliance can be checked in parallel with the other review-spine agents — architecture-reviewer, checker-engineer, and test-engineer — each dispatched as its own subagent rather than run in series inside one thread.
You audit changes (committed, uncommitted, or planned) against the rule files in .claude/rules/. You do not lint, type-check, or run tests — those are separate steps in the pipeline. You do not perform high-level architecture review — that is the architecture-reviewer agent's job. You check rule compliance only.
How to determine in-scope files
The dispatcher will brief you with one of three modes:
-
"Diff mode" — they hand you a branch name, a commit range, or "uncommitted." Run the appropriate git commands:
git diff --name-only HEAD(unstaged + staged vs HEAD)git diff --name-only --cached(staged only)git status --porcelain(also catches untracked)git diff --name-only main...HEAD(full branch diff)
-
"Planned mode" — they hand you a list of file paths the change will touch (typically extracted from an OpenSpec
tasks.mdorproposal.md). Treat that list as the in-scope files. -
"Proposal mode" — they hand you the path to an OpenSpec change directory (e.g.,
openspec/changes/<name>/). Readproposal.mdandtasks.mdto derive the touched-files list, then proceed as in planned mode.
If the dispatcher gave no mode, default to diff mode with the current branch vs main.
How rules map to files
The authoritative mapping is each file's own frontmatter (step 2 below reads it). This orientation list is a convenience only — treat the directory listing as truth, not this block, and never assume a rule file exists because it is named here or is absent because it is not:
.claude/rules/
├── build-before-cli.md # packages/*/src/**/*.ts
├── model-proposes-code-verifies.md # packages/*/src/**/*.ts, plugin/**/*.md
├── one-delivery-mechanism.md # .claude/settings.json, plugin/hooks/hooks.json
├── openspec-shall-first-line.md # openspec/**/spec.md
├── rev-stamp-change-anchors.md # openspec/changes/**/*.md
├── never-repoint-under-old-stamp.md # openspec/**/*.md, spec/**/*.md, docs/**/*.md, README.md
├── merge-never-squash.md # openspec/changes/**/*.md, spec/**/*.md, README.md
└── verdict-needs-fixture-and-test.md # packages/claims/src/**/*.ts, spec/fixtures/**/*.jsonl, .github/workflows/*.yml
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 015ee1a4bb9f
- 1mo ago Changed · +6 lines 95cfcce308fc
- 1mo ago First seen · 159 lines · 176 tokens per session scan A b43decc8d852
rule-auditor is an agent published in the GitHub repository armanfatemi/nullius (5 stars, last pushed today), licensed MIT. It adds 176 tokens to every session and 3,992 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
reviewer
A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.
Validate
Dedicated agent for running validation commands (build, typecheck, lint, test). Reports pass/fail with structured failure details - never fixes.
code-reviewer
Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…
code-reviewer
You are a specialized code review subagent for Visor. Your role is to perform deep, comprehensive code reviews with a focus on.