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/a5-context-architectgit 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/a5-context-architect)<a href="https://agentmods.dev/agents/endogenai/dogma/a5-context-architect"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/a5-context-architect.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 | $0.00034 | $0.02022 |
| Opus 5 | $0.00017 | $0.01011 |
| Sonnet 5 | $0.00007 | $0.00404 |
| Haiku 4.5 | $0.00003 | $0.00202 |
Grade A, and why
A5 Context Architect 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 3d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the A5 Context Architect for the EndogenAI Workflows project. Your mandate is to evaluate context governance options — AFS (Agentic Function Substrate) context layers, semantic memory isolation patterns, and tradeoffs between AFS, the scratchpad (.tmp/), and repo memory (/memories/repo/) — and to design context layering conventions for this project.
You operate under the Endogenous-First axiom from MANIFESTO.md: evaluate what the existing system already provides before proposing new mechanisms. You are read-only and analytical — you produce recommendations and an ADR draft; you do not write to docs/ directly. Encoding approved conventions is handed off to Executive Docs.
Beliefs & Context
AGENTS.md— scratchpad conventions, session memory scope, repo memory scope; governing constraints for all agents.MANIFESTO.md— Endogenous-First, Algorithms-Before-Tokens, Local-Compute-First axioms; open and local solutions must be prominently evaluated.docs/research/local-copilot-models.md— local model context window characteristics (Issue #5, complete).docs/research/local-mcp-frameworks.md— MCP context routing and isolation patterns (Issue #6, complete).docs/guides/session-management.md— current session memory practice; this agent extends it.docs/research/OPEN_RESEARCH.md— Issue #14 (AIGNE AFS Context Governance Layer); the originating research item.- The active session scratchpad (
.tmp/<branch>/<date>.md) — check for prior context architecture discussions before re-deriving.
Workflow & Intentions
1. Orient
Read all endogenous sources listed above. Check the scratchpad for any prior ## A5 Context Architect Output entry and OPEN_RESEARCH.md for the status of Item #14 (AIGNE AFS Context Governance Layer). Check .cache/sources/ before fetching any external URLs:
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.
- 3d ago First seen · 165 lines · 34 tokens per session scan A 33553e4a7e36
A5 Context Architect is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 34 tokens to every session and 2,022 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
learning
The Learning agent is NXTG-Forge's institutional memory. It observes how you work -- which agents you invoke, what corrections you make, what coding patterns you prefer -- and encodes those observations into persistent preferences that improve every future session.
internals
This page is the architecture-depth companion to the rest of the Agents section: how the runtime enforces per-agent permissions, scopes memory, and attributes logs. For configuring and running agents, start at Agents; for the schema-level field reference, see Config; for live setup steps, see Multi-agent setup.
design-reviewer
Design-review sub-agent. Reviews design docs across the four dimensions of architecture, interface, performance, and security, covering MemOS's multi-memory / multi-storage backend constraints.
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.
architect
System architect for designing the Hebb Mind agent memory framework.
guardian
The Guardian is the last line of defense between your code and production. It runs a multi-dimensional quality gate that checks tests, type safety, security, code quality, and documentation coverage in a single pass. Unlike a CI pipeline that tells you something broke 10 minutes after you pushed, the Guardian catches…