anti-slop-secretary

anti-slop-secretary is an agent for Claude Code from AgriciDaniel/anti-slop. It costs 83 tokens per session (722 once invoked), scanned A, original, Apache-2.0.

A read-only assistant for checking prose, code, documentation, and agent output against cited source material. It focuses on signs of unsupported or low-quality content, not on guessing who wrote it.

In plain words
What is it for?
Use it to review claims, find unsupported wording, maintain a source collection, and prepare advisory repair or release-hygiene checks.
Why use it?
It helps replace vague opinions about writing quality with evidence from a reference collection. It also keeps source checking, claim review, and release checks organized.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md; mentions Codex.

Part of the anti-slop-brain plugin — 1 skill, 4 agents shipped together

Good fit Use it to review claims, find unsupported wording, maintain a source collection, and prepare advisory repair or release-hygiene checks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/agricidaniel/anti-slop/anti-slop-secretary
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/AgriciDaniel/anti-slop

Made for: Claude Code.

Or install anti-slop-brain, the plugin that ships this one along with the rest of its 1 skill, 4 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 anti-slop-secretary

README.md
[![agentmods](https://agentmods.dev/badge/agents/agricidaniel/anti-slop/anti-slop-secretary/github.svg)](https://agentmods.dev/agents/agricidaniel/anti-slop/anti-slop-secretary)
Your own site
<a href="https://agentmods.dev/agents/agricidaniel/anti-slop/anti-slop-secretary"><img src="https://agentmods.dev/badge/agents/agricidaniel/anti-slop/anti-slop-secretary/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 anti-slop-secretary

Your own site · 80×15
<a href="https://agentmods.dev/agents/agricidaniel/anti-slop/anti-slop-secretary"><img src="https://agentmods.dev/badge/agents/agricidaniel/anti-slop/anti-slop-secretary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 722 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 $0.00083 $0.00722
Opus 5 $0.00042 $0.00361
Sonnet 5 $0.00017 $0.00144
Haiku 4.5 $0.00008 $0.00072

Measured 13d ago against content hash a2ed8d055e1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

anti-slop-secretary 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 13d 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.

anti-slop-brain/agents/anti-slop-secretary.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anti-Slop Brain Secretary

You are the grounded secretary for Anti-Slop Brain, an advisory read-only brain for detection and repair of AI slop in prose, code, documentation, and agent output, grounded in corpus evidence rather than authorship detection.

Always Do This First

Resolve repo-root paths from the product or skill repo root. Resolve vault-root paths from the deployed vault root, the directory containing CODEX.md, wiki/, and .raw/. In this repo the template vault root is assets/template-brain/; the demo vault root is examples/sample-vault/; client vault roots are the folders passed with --vault.

Read repo-root instructions in this order: AGENTS.md, SKILL.md, README.md, docs/OPERATOR_KIT.md, docs/PRODUCT_BOUNDARIES.md, references/source-ledger.json, and references/adapter-manifest.json.

Then read vault-root instructions in this order: <vault>/CODEX.md, <vault>/wiki/hot.md, <vault>/wiki/index.md, <vault>/wiki/meta/CONVENTIONS.md, the relevant <vault>/wiki/<folder>/_index.md, and the specific note. If those paths are missing in the current directory, locate the vault root before answering.

Answer Contract

  • Answer from the brain first.
  • Cite the vault note by title and path.
  • Cite an official, primary, vendor, regulator, standards-body, or API URL for any domain claim.
  • If the brain lacks the answer, say no data, name the missing source, and propose a source-ledger update.
  • Mark every claim with one confidence tag from references/CONFIDENCE_TAGS.md.
  • Use references/claim-ledger.md for adversarial checks and SINGLE-SOURCE marking.

Honest Limits

  • This scaffold does not contain current domain facts yet.
  • Evidence past refresh cadence is stale until re-verified: 30 days for model-specific marker cohorts and detector claims; 90 days for corpus studies and regulation; before every release for any numeric claim.
  • Corpus scope follows: each corpus note states harness, date, source, and non-scope.
  • Second-source policy follows: required for market, current, comparative, numeric, and high-stakes claims.

Read the full file on GitHub · 48 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. 13d ago First seen · 48 lines · 83 tokens per session scan A a2ed8d055e1d

Subscribe to this mod's changes

anti-slop-secretary is an agent published in the GitHub repository AgriciDaniel/anti-slop (50 stars, last pushed yesterday), licensed Apache-2.0. It adds 83 tokens to every session and 722 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 2026-08-30.

Related

Other agents, from other repositories

ui-spec-designer

Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.

shinpr/claude-code-workflows · 40 tokens

ring:qa

Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.

LerianStudio/ring · 52 tokens

lead

Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.

nguyenthienthanh/aura-frog · 28 tokens

replanner

Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.

nguyenthienthanh/aura-frog · 57 tokens

review-rails

Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.

hoblin/claude-ruby-marketplace · 64 tokens

evolve-retrospective

Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.

mickeyyaya/evolve-loop · 51 tokens