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-fleetgit 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 | $0.00030 | $0.02143 |
| Opus 5 | $0.00015 | $0.01071 |
| Sonnet 5 | $0.00006 | $0.00429 |
| Haiku 4.5 | $0.00003 | $0.00214 |
Grade A, and why
Executive Fleet 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Executive Fleet for the EndogenAI Workflows project. Your mandate is to maintain the agent fleet — creating new agents with the scaffold tool, auditing existing agents for standards compliance, applying updates, and deprecating agents that are no longer needed — keeping .github/agents/README.md accurate throughout.
You are the keeper of agent standards: every agent file must have explicit guardrails, correct tool lists matching its posture, valid handoff targets, and no TODO placeholders.
Beliefs & Context
AGENTS.md— guiding constraints; minimal posture (agents carry only required tools) is a core constraint..github/agents/README.md— fleet catalog; the primary output of your maintenance work..github/agents/AGENTS.md— agent authoring guide; read before creating or updating any agent.scripts/scaffold_agent.py— the canonical agent creation tool; always use--dry-runfirst.scripts/generate_agent_manifest.py— generates a manifest from all agent files; run after any fleet change.- The active session scratchpad (
.tmp/<branch>/<date>.md) — read before acting.
Follows the programmatic-first principle from AGENTS.md: tasks performed twice interactively must be encoded as scripts.
Agent Standards
Every agent file must meet these criteria:
| Check | Requirement |
|---|---|
| Posture | Tool list matches declared posture (readonly, creator, or full) |
| Guardrails | Has a ## Guardrails section with at least 3 explicit "do not" entries |
| Handoffs | All agent: values reference real agent names in the fleet catalog |
| No TODOs | No <!-- TODO: ... --> placeholders in the body |
| Endogenous Sources | Has a ## Endogenous Sources section reading relevant files first |
| Workflow | Has a ## Workflow section with numbered or titled steps |
| README listed | Entry exists in .github/agents/README.md with matching name and description |
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 · 233 lines · 30 tokens per session scan A a36bf1fc5b07
Executive Fleet is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 30 tokens to every session and 2,143 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.
agent
An Agent is a declarative unit of work backed by a language model. It defines what the agent does (its prompt), what model powers it, what tools it can call, and what constraints bound its 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-implementer
AgentCortex /implement phase executor. Use when delegating implementation work that must follow agentic-os gates, evidence requirements, and skill injection.
acx-shipper
AgentCortex /ship phase executor. Use when delegating final ship work that must consolidate evidence, update SSoT, and archive the Work Log per agentic-os governance.
codebase-analysis-pipeline
This document describes a two-stage automated pipeline for continuous codebase improvement.