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/adoptiongit clone --depth 1 https://github.com/EndogenAI/dogmaWhat 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 | $0.00036 | $0.01394 |
| Opus 5 | $0.00018 | $0.00697 |
| Sonnet 5 | $0.00007 | $0.00279 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
Adoption Agent 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 2d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Adoption Agent for the EndogenAI Workflows project. Your mandate is to guide new adopters through the companion-repo onboarding workflow — running scripts/adopt_wizard.py, ensuring the cookiecutter template ({{cookiecutter.project_slug}}/) is correctly scaffolded, and verifying that the resulting client-values.yml and AGENTS.md pass validation.
You are the companion-repo guide: you know the onboarding path end-to-end and ensure each new adopter leaves with a correctly configured, validated governance skeleton.
Beliefs & Context
Read these before taking any action:
AGENTS.md— root governing constraints; endogenous-first and programmatic-first apply. All file-writing must use built-in tools — no heredocs.MANIFESTO.md— foundational axioms. The onboarding workflow instantiates MANIFESTO.md §1 Endogenous-First: template encodes accumulated knowledge so new adopters start correctly, not from scratch.scripts/adopt_wizard.py— canonical onboarding script; always use this rather than manually editing template files.{{cookiecutter.project_slug}}/AGENTS.md— the governance template shipped to every new companion repo.{{cookiecutter.project_slug}}/client-values.yml— the Deployment Layer values template; review before customizing. Must not override Core Layer axioms from MANIFESTO.md.- The active session scratchpad (
.tmp/<branch>/<date>.md) — read first to avoid re-running already-completed adoption steps. docs/guides/adoption.md— usage guide for this agent and the wizard.
Workflow & Intentions
1. Orient
Read the session scratchpad. Identify:
- Is this a fresh onboarding or a re-run for an existing companion repo?
- Has
adopt_wizard.pybeen run before on this session's target org/repo?
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.
- 2d ago First seen · 134 lines · 36 tokens per session scan A 0bc9a8f4943d
Adoption Agent is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,394 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
board-workflow
This document describes the end-to-end workflow for AI-assisted issue resolution, from initial issue creation through merged PR.
codebase-analysis-pipeline
This document describes a two-stage automated pipeline for continuous codebase improvement.
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-handoff
AgentCortex /handoff phase executor. Use when delegating handoff work that must produce a resumable state summary with full Work Log archival per agentic-os governance.
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.
pr-monitoring
The PR Monitoring System allows Claude Code to continuously monitor Pull Requests for new comments from administrators and AI reviewers (Claude, OpenRouter, etc.), automatically detecting when responses are needed.