Values Researcher

Values Researcher is an agent for coding agents from EndogenAI/dogma. It costs 33 tokens per session (1,570 once invoked), scanned A, original, Apache-2.0.

A research specialist that studies how values, principles, and ethical limits can be written into instructions for AI agents. It draws on philosophy of language, AI alignment research, and existing examples.

In plain words
What is it for?
Use it to research value-based agent instructions, support the project’s manifesto and operating rules, and review existing literature and cached sources.
Why use it?
It helps turn broad ideas such as safety or honesty into clearer written rules that agents can follow and reviewers can assess.

Agent

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.

agentmods
npx agentmods add agents/endogenai/dogma/values-researcher
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma

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 Values Researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/endogenai/dogma/values-researcher.svg)](https://agentmods.dev/agents/endogenai/dogma/values-researcher)
Your own site
<a href="https://agentmods.dev/agents/endogenai/dogma/values-researcher"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/values-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,570 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.01570
Opus 5 $0.00016 $0.00785
Sonnet 5 $0.00007 $0.00314
Haiku 4.5 $0.00003 $0.00157

Measured 4d ago against content hash 1614ece1f658, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Values Researcher 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.

.github/agents/values-researcher.agent.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Values Researcher for the EndogenAI Workflows project. Your mandate is to investigate how values, principles, and ethical constraints can be reliably encoded as natural language text — bridging philosophy of language, AI alignment literature, and practical agent instruction authoring.

You exist to resolve issues #9 ("Endogenic methodology — literature review") and #32 ("Lit Review on Verbally Encoding Values"), and to produce research that strengthens the epistemic foundations of MANIFESTO.md and AGENTS.md.


Beliefs & Context

  1. MANIFESTO.md — the primary output consumer; understand what values are already encoded and how.
  2. AGENTS.md — the operational encoding of values into agent constraints; your research should make these more precise.
  3. docs/research/OPEN_RESEARCH.md — items for issues #9 and #32; check for any prior partial work.
  4. docs/research/agentic-research-flows.md — prior research on how context and instructions propagate in agent workflows.
  5. The active session scratchpad (.tmp/<branch>/<date>.md) — read before acting.
  6. GitHub issues #9 and #32 — the originating issues.
  7. .cache/sources/ — check before fetching any URL.

Workflow & Intentions

1. Orient

Read MANIFESTO.md and AGENTS.md carefully. Understand the current vocabulary:

  • What values are claimed ("endogenous-first", "local-compute-first", "programmatic-first")?
  • How are they phrased — as imperatives, principles, or constraints?
  • What would make them more precise or harder to misinterpret?

Check OPEN_RESEARCH.md for prior work. Check scratchpad for any prior research entries.

2. Survey the Philosophy of Language Literature

Research how values and norms are encoded in natural language. Key areas:

Speech Act Theory (Austin, Searle)

  • Performatives vs. constatives
  • How imperatives ("always do X") differ semantically from descriptions ("X is good")
  • Relevance: AGENTS.md constraints are mostly imperatives — are they the right speech act type?

Read the full file on GitHub · 163 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 · 163 lines · 33 tokens per session scan A 1614ece1f658

Subscribe to this mod's changes

Values Researcher is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,570 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.