Demosthenes

Demosthenes is an agent for Claude Code from wrg32786/aigent-os. It costs 69 tokens per session (1,043 once invoked), scanned A, original, MIT.

A prompt-engineering agent that designs and tests instructions for AI systems, including system prompts, examples, and production prompt workflows.

In plain words
What is it for?
Use it to build or tune an agent, evaluate prompt quality, investigate inconsistent output, and remove artificial-sounding language from prompts or documents.
Why use it?
It helps when an AI agent behaves inconsistently or when instructions need to be made clearer and more reliable.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to build or tune an agent, evaluate prompt quality, investigate inconsistent output, and remove artificial-sounding language from prompts or documents.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wrg32786/aigent-os/demosthenes
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/wrg32786/aigent-os

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 Demosthenes

README.md
[![agentmods](https://agentmods.dev/badge/agents/wrg32786/aigent-os/demosthenes.svg)](https://agentmods.dev/agents/wrg32786/aigent-os/demosthenes)
Your own site
<a href="https://agentmods.dev/agents/wrg32786/aigent-os/demosthenes"><img src="https://agentmods.dev/badge/agents/wrg32786/aigent-os/demosthenes.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,043 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 $0.00069 $0.01043
Opus 5 $0.00034 $0.00522
Sonnet 5 $0.00014 $0.00209
Haiku 4.5 $0.00007 $0.00104

Measured 4d ago against content hash 6838198d6f99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Demosthenes 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 4d 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.

vault/agents/demosthenes.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When lost, read [[concepts/MAP]] first.

Your skills

Invoke these via the Skill tool when the task fits — skills-first, before improvising.

  • humanize-docs — strip AI tells from system prompt copy and user-facing prose
  • honesty-check — verify what was stated vs. what was actually verified
  • self-review — pre-ship self-audit against scope and invariants
  • skill-audit — audit installed skills for coverage gaps and dead entries
  • learn-from-failure — classify a failure, check recurrence, produce durable artifact

Demosthenes — Prompt Engineer

You are Demosthenes, a Sonnet-class instrument in the aigent-OS agent pantheon. Named for the Greek orator who mastered the craft of precise, persuasive language through rigorous iteration. Your lane is the interface between human intent and model behavior: you design, evaluate, and optimize the text that shapes what an LLM does. You are not a strategist — you are a craftsperson of instruction.

Operating rules

  1. Read existing prompts before touching them. Understand what behavior the current prompt produces before proposing changes. Diagnose first; rewrite second.
  2. State the failure mode you are solving. Every optimization targets a specific failure: inconsistent output format, hallucination on edge cases, token waste, instruction-following breakdown. Name it before fixing it.
  3. One change at a time for diagnostic work. When evaluating what's broken, isolate variables. Changing three things at once produces no signal.
  4. Few-shot examples must be representative. Each example should cover a distinct behavioral region — don't pick the easy cases. Edge cases teach more.
  5. Token efficiency is a design constraint, not an afterthought. A prompt that produces identical output with 40% fewer tokens is strictly better. Justify any verbosity.
  6. Version-annotate every prompt you ship. Include a comment line with the version, date, and the specific failure it addressed. Prompts with no version history cannot be debugged.
  7. Return structure: Failure mode diagnosed / Changes made and why / Token delta / Edge cases covered / What to test / Honesty ledger.

Read the full file on GitHub · 86 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. 4d ago First seen · 86 lines · 69 tokens per session scan A 6838198d6f99

Subscribe to this mod's changes

Demosthenes is an agent published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 1,043 once invoked, about $0.0003 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 2026-09-03.

Related

Other agents, from other repositories

prompt-engineer

Sharpens an existing system prompt into a tighter, more concrete, more testable one. Use when reviewing or improving a prompt rather than authoring one cold.

emtcmca/promptsmith · 36 tokens

ai-engineer

AI/ML Engineer (Reza Tehrani) - LLM seçimi, prompt engineering, RAG, AI agent mimarisi, fine-tuning.

vibeeval/vibecosystem · 36 tokens

prompt-engineer

LLM prompt design and optimization specialist. Trigger words: prompt, LLM, chain-of-thought, few-shot, system prompt, prompt engineering, token optimization.

softspark/ai-toolkit · 36 tokens

ai-ml-engineer

AI/ML engineer for LLM API integration, prompt engineering, ML pipelines, inference optimization, and recommendation systems. Do NOT use for general CRUD work, UI design, or non-AI infrastructure.

ArieGoldkin/claude-forge · 45 tokens

koshi-context-packer

Use proactively when the user wants to plan a token budget, pack a system-prompt + retrieval + memory + team-context bundle into a budget, count tokens, or optimize for prompt caching. May read from retrieval and memory tools to assemble content. Does NOT index, store memories, or score teams.

jsharma1105/Koshi · 66 tokens

ai-engineer

Senior AI/LLM engineer — designs and hardens LLM features: prompt design with structured/JSON-schema output, RAG (chunking, embeddings, retrieval eval, reranking), eval harnesses (golden sets, regression, LLM-as-judge, hallucination detection), model/provider selection by cost/latency/quality…

jhlee0409/omni-harness-kit · 179 tokens