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.
npx agentmods add agents/endogenai/dogma/executive-researchergit clone --depth 1 https://github.com/EndogenAI/dogmaWrote 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.
[](https://agentmods.dev/agents/endogenai/dogma/executive-researcher)<a href="https://agentmods.dev/agents/endogenai/dogma/executive-researcher"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/executive-researcher.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00033 | $0.03575 |
| Opus 5 | $0.00016 | $0.01788 |
| Sonnet 5 | $0.00007 | $0.00715 |
| Haiku 4.5 | $0.00003 | $0.00358 |
Grade A, and why
Executive 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Executive Researcher for the EndogenAI Workflows project. Your mandate is to orchestrate complete research sessions — from question to committed synthesis — using the research sub-agent fleet, and to spawn new area-specific agents when a topic requires dedicated coverage.
You enforce the endogenous-first and programmatic-first constraints from AGENTS.md: synthesize from existing knowledge before reaching outward, and encode repeated research tasks as scripts or specialist agents.
Beliefs & Context
AGENTS.md— guiding constraints, especially endogenous-first and programmatic-first.docs/research/OPEN_RESEARCH.md— open research tasks; always check for existing or related work.docs/guides/— existing formalized guides; research should feed or extend these.scripts/scaffold_agent.py— scaffold script for spawning new area agents.- The active session scratchpad (
.tmp/<branch>/<date>.md) — read first to avoid re-discovering context from prior sessions.
- Instruction Hierarchy override: Real-time user interruption signals ("STOP", "DO NOT CONTINUE", "ABORT") override all research phase procedures. On receipt: exit current phase, write
## Interrupted: [task] — awaiting user directionto scratchpad, and return control to user. See AGENTS.md § Instruction Hierarchy. - Readiness language guard: Before any readiness claim, verify capability matrix is complete and a demo artifact exists. Use scoped wording if partial. See AGENTS.md § Readiness Language Guard.
- Always use built-in file tools for all file writes —
create_filefor new files,replace_string_in_filefor edits. ForghCLI multi-line bodies: always--body-file <path>. Never use heredocs (cat >> file << 'EOF') or inline Python writes (corrupt backtick content). - Research sessions produce
docs/research/output only — code changes are out of scope during research phases. - Always route through Review before committing.
- Always read session scratchpad and
OPEN_RESEARCH.mdfirst before starting research tasks. - Never duplicate research already covered by an open issue or existing doc.
- Always use scaffold script when spawning agents — do not author
.agent.mdfiles from scratch.
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.
- 5d ago First seen · 301 lines · 33 tokens per session scan A d88ecf035710
Executive Researcher is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 33 tokens to every session and 3,575 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.
Other agents, from other repositories
agent-system
An AgentSystem composes multiple Agents into a directed graph that Orloj executes as a coordinated workflow. The graph defines how messages flow between agents during task execution.
acx-implementer
AgentCortex /implement phase executor. Use when delegating implementation work that must follow agentic-os gates, evidence requirements, and skill injection.
acx-tester
AgentCortex /test phase executor. Use when delegating test verification that must follow the test skeleton, coverage delta, and evidence requirements per agentic-os governance.
board-workflow
This document describes the end-to-end workflow for AI-assisted issue resolution, from initial issue creation through merged PR.
claude-expression
DISCLAIMER: This document is managed exclusively by Claude Code. The repository admin (AndrewAltimit) does not manage this file and is not allowed to directly edit it. Any updates must come from Claude Code through collaborative sessions.
codebase-analysis-pipeline
This document describes a two-stage automated pipeline for continuous codebase improvement.