nullius: Skill for Claude Code

.claude/skills/advise-specialized-agents/SKILL.md

advise-specialized-agents is a skill for Claude Code from armanfatemi/nullius. It costs 0 tokens per session (6,826 once invoked), scanned A, original, MIT.

A review workflow that asks four specialised agents to examine a proposed change or its code diff. The reviewers cover repository rules, architecture, decision-making checks, and test coverage.

In plain words
What is it for?
Use it to select relevant reviewers, justify why they apply, collect their advice, and review either an OpenSpec proposal or the resulting code changes.
Why use it?
It helps identify problems from several focused viewpoints instead of relying on one general review. The workflow also records the review evidence for later use.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is armanfatemi/nullius's own configuration. It tells Claude Code how to work on nullius itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nullius configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/armanfatemi/nullius/main/.claude/skills/advise-specialized-agents/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/armanfatemi/nullius

Made for: Claude Code.

Wrote 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.

agentmods badge for advise-specialized-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/armanfatemi/nullius/advise-specialized-agents/github.svg)](https://agentmods.dev/skills/armanfatemi/nullius/advise-specialized-agents)
Your own site
<a href="https://agentmods.dev/skills/armanfatemi/nullius/advise-specialized-agents"><img src="https://agentmods.dev/badge/skills/armanfatemi/nullius/advise-specialized-agents/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.

agentmods 80×15 button for advise-specialized-agents

Your own site · 80×15
<a href="https://agentmods.dev/skills/armanfatemi/nullius/advise-specialized-agents"><img src="https://agentmods.dev/badge/skills/armanfatemi/nullius/advise-specialized-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,826 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

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 →

  • medium Agent Snooping · line 22
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Output Handling · line 247
    Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.
    Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.06826
Opus 5 $0.00000 $0.03413
Sonnet 5 $0.00000 $0.01365
Haiku 4.5 $0.00000 $0.00683

Measured 8d ago against content hash 8055aa12a45e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

advise-specialized-agents 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 8d 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.

.claude/skills/advise-specialized-agents/SKILL.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specialist agent consultation

Four reviewer agents live in .claude/agents/. Each reads a different body of doctrine, and the boundaries between them are drawn in their own files rather than left to the dispatcher's judgement: rule-auditor reads the glob-scoped rule files, architecture-reviewer reads the prose invariants that nothing scopes, checker-engineer reads the four kernel modules that decide a verdict, and test-engineer reads whether the coverage proves what it claims. This skill is the protocol for asking them to review or advise on work.

proposal-to-pr now consumes their reports (.claude/skills/proposal-to-pr/SKILL.md). It dispatches this roster twice — at Stage 2 against the proposal, at Stage 6 against the diff — routes on the severity markers below, appends the synthesis to the change's committed review-evidence.md, and hands that file to retro-writer. It borrows the pre-flight and synthesis doctrine from this file rather than carrying a second copy, so the two must not drift.

That covers work with an openspec/changes/<name>/ behind it. Everything else is dispatched by hand through this skill, and there nothing automatic is watching: you are the reader of every report these agents produce, and the synthesis step below is the only place their findings get reconciled.

The roster is declared twice, and the two must agree

The frontmatter above carries dispatches:. That list is the roster — the one nullius wiring actually reads, because its hard verdicts resolve declared frontmatter fields and nothing else:

Evidence: packages/claims/src/wiringScan.ts:156@555e5eedispatches: declaredList(front, "dispatches"),

The table further down repeats the same four names for a human deciding whom to dispatch. A name added to that table and not to the frontmatter is a roster entry nobody checks: if the agent behind it does not exist, the dispatch no-ops, and the run reports a review that never happened. That is precisely what DANGLING-AGENT exists to catch and precisely what it cannot see in a markdown table. Adding a fifth agent means editing both surfaces. Treat the frontmatter as the roster and the table as its documentation — never the reverse.

Read the full file on GitHub · 410 lines

Changes

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.

  1. 8d ago First seen · 410 lines · 0 tokens per session scan A 8055aa12a45e

Subscribe to this mod's changes

advise-specialized-agents is a skill published in the GitHub repository armanfatemi/nullius (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,826 tokens. 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.

Related

Other skills, from other repositories

argot-setup

Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…

get-tmonier/argot · 129 tokens

argot-check

Score your working changes with argot — flag code foreign to this repo's own patterns (unfamiliar dependencies, APIs, constructs), functions the repo already has, code filed in the wrong place, imports that break the repo's layering, and tests weakened, disabled, or deleted alongside a production change — before…

get-tmonier/argot · 110 tokens

argot-write-rule

Codify a repo convention argot's built-ins don't cover into a scripted custom rule — a .argot/rules/NAME/rule.toml manifest plus a sandboxed Rhai script that fires exactly like a built-in, gated on a green fixture suite before it ever sees a real diff. Use when the user asks to "write an argot rule for X", "codify…

get-tmonier/argot · 131 tokens

argot-review-pr

Review a specific pull request (or diff range) against this repo's learned patterns with argot, without checking it out — flag dependencies, APIs, and constructs foreign to how the repo is written, duplicated functions, misfiled code, layering breaks, and tests weakened, disabled, or deleted alongside a production…

get-tmonier/argot · 78 tokens

argot-suggest-rules

Turn a convention argot has already discovered into a scripted custom rule. Runs argot conventions, surfaces the repo's mined placement conventions (where a kind of code lives — "validation in schema files", "DB access only in migrations", "business logic in the service layer, not views") and internal-API vocabulary…

get-tmonier/argot · 173 tokens

bellwether

Bring the current PR to a mergeable state: CI green, all review comments resolved, no merge conflicts. Self-contained — watches CI, fixes issues, watches again until merge-ready. Use when the user wants to keep a PR green, auto-fix CI, resolve review comments, or says "get this merged".

roderik/bellwether · 68 tokens