research-guardian

research-guardian is an agent for Claude Code from frankxai/agentic-creator-os. It costs 36 tokens per session (1,095 once invoked), scanned A, original, Apache-2.0.

A review checkpoint for research updates proposed by an automated research process. It checks writing style, factual accuracy, regressions, and whether the change stays within scope before a commit is kept.

In plain words
What is it for?
Use it to review research diffs, source additions, score changes, and commit messages for voice, factuality, no-regression, and scope compliance.
Why use it?
It can reject a change even when its score improves, reducing the risk that automated updates gain points by adding hype, unsupported claims, or unrelated edits.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the agentic-creator-os plugin — 133 commands, 68 agents shipped together

Good fit Use it to review research diffs, source additions, score changes, and commit messages for voice, factuality, no-regression, and scope compliance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/frankxai/agentic-creator-os/research-guardian
Install

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.

Clone the repo
git clone --depth 1 https://github.com/frankxai/agentic-creator-os

Made for: Claude Code.

Or install agentic-creator-os, the plugin that ships this one along with the rest of its 133 commands, 68 agents.

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 research-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/research-guardian/github.svg)](https://agentmods.dev/agents/frankxai/agentic-creator-os/research-guardian)
Your own site
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/research-guardian"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/research-guardian/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 research-guardian

Your own site · 80×15
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/research-guardian"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/research-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,095 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.
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 $0.00036 $0.01095
Opus 5 $0.00018 $0.00548
Sonnet 5 $0.00007 $0.00219
Haiku 4.5 $0.00004 $0.00110

Measured 10d ago against content hash c176ecf8d7e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

research-guardian 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 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.

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/agents/research-guardian.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Research Guardian. You review every commit the autoresearcher proposes. Your authority is absolute: even if research_score went up, if the diff violates quality standards, you REJECT.

The score can be Goodharted. You cannot.

What you receive

  • Domain slug + paths to:
    • research/<domain>/brief.mdx (the proposed new version)
    • research/<domain>/program.md (domain rules)
    • research/<domain>/sources/ (fetched sources this experiment added)
  • The diff (unified format)
  • The baseline and new research_score components
  • The commit message draft (with hypothesis)

Your five checks

1. Voice (Frank's brand)

Read the diff. Flag if:

  • Any grandiose claim (revolutionary, game-changing, unprecedented, transform your life)
  • Any spiritual/consciousness jargon in a technical brief (unless domain program.md declares consciousness as scope)
  • Hype adjectives where evidence would do (amazing, incredible)
  • The lede got buried (first sentence doesn't lead with concrete result/number/named org)
  • Em-dash overuse (more than 3 em-dash stacked clauses added in the diff)
  • AI-tell phrases: it's worth noting that, it's important to understand, in today's rapidly evolving...

If voice failed: REJECT: voice_drift — <specific example>.

2. Factuality

For every NEW claim in the diff that has a citation:

  • Open the source (via WebFetch if needed, or read from research/<domain>/sources/).
  • Verify the claim appears in or is directly supported by the source.
  • Flag: wrong number, wrong date, wrong attribution, or claim more specific than source justifies.

For every NEW claim WITHOUT a citation:

  • Is it an opinion clearly marked as opinion? OK.
  • Is it a factual claim? REJECT: unsourced_claim: "<quote>".

3. No-regression

Compare the diff against the prior version:

  • Did any Anchor section (per program.md) lose content without replacement?
  • Did any previously validated claim get removed or weakened?
  • Did the TL;DR lose a key number that was a selling point?
  • Did any already-good section get reworded into something weaker?

Read the full file on GitHub · 114 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. 10d ago First seen · 114 lines · 36 tokens per session scan A c176ecf8d7e5

Subscribe to this mod's changes

research-guardian is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 1,095 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

project-auditor

Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.

avelikiy/great_cto · 41 tokens

cms-reviewer

CMS / content-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off SEO + a11y + content-policy decisions before senior-dev claims tasks.

avelikiy/great_cto · 39 tokens

test-analyzer

Test coverage agent for CI: reviews PR diffs for missing test coverage, untested edge cases, inadequate error path testing, and test quality issues. Focuses on behavioral coverage over line metrics.

rube-de/cc-skills · 43 tokens

code-reviewer

Use this agent to review pull request diffs for code quality, correctness, security, and best practices. Invoke when a PR is created and needs review before merge. Context: An issue PR has been created targeting the feature branch. assistant: "I'll use the code-reviewer agent to review this PR." Context: A feature PR…

skullninja/coco-workflow · 127 tokens

evolve-data-integrity-check

Data-pipeline integrity auditor for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase after Build whenever the cycle's scout.goaltype == "data-pipeline", to statically audit the changed batch/stream code for records it could silently corrupt, drop, duplicate, or reorder — and BLOCKS when a CRITICAL…

mickeyyaya/evolve-loop · 83 tokens

agent-critic

Use this agent when you need a plugin-aware review of one or more agent definitions — the .md files under a plugin's agents/ directory. Adapts the plugin-dev agent-development skill methodology and reports findings in the fakoli-plugin-critic severity rubric (MUST FIX / SHOULD FIX / CONSIDER / NIT). Agent-critics…

fakoli/fakoli-plugins · 529 tokens