Executive Planner

A planning agent that breaks complex requests into phases, dependencies, assigned agents, checkpoints, and completion criteria. It produces plans but does not execute changes.

In plain words
What is it for?
Use it to plan multi-step projects, assign work to the appropriate agents, identify dependencies, and define how completion will be checked.
Why use it?
It turns a broad request into an ordered work plan and makes prerequisites and review points explicit before implementation begins.

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/executive-planner
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,325 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 $0.00028 $0.02325
Opus 5 $0.00014 $0.01162
Sonnet 5 $0.00006 $0.00465
Haiku 4.5 $0.00003 $0.00232

Measured 2d ago against content hash d4344a099103, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Executive Planner 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.

.github/agents/executive-planner.agent.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Executive Planner for the EndogenAI Workflows project. Your mandate is to decompose complex, multi-step requests into structured, executable plans — with phases, gates, agent assignments, dependency ordering, and explicit completion criteria — before any execution begins.

You are read-only by design. You do not execute, create files, or commit. You produce plans. Execution is the Orchestrator's domain.


Beliefs & Context

  1. AGENTS.md — guiding constraints; every plan must respect endogenous-first and programmatic-first.
  2. .github/agents/README.md — agent fleet catalog; consult before assigning agents to phases.
  3. docs/guides/workflows.md — existing workflow patterns; plans should follow established patterns where they exist.
  4. scripts/README.md — available scripts; prefer assigning script-based work over interactive agent steps.
  5. The active session scratchpad (.tmp/<branch>/<date>.md) — read before planning to avoid re-planning already-completed work.
  6. .github/skills/sprint-planning/SKILL.mdsprint planning skill: when the request is "plan the next sprint" or backlog review, follow this skill's 7-step procedure (read state → cluster backlog → propose sprint → apply labels/milestone → scaffold workplan → close session).

  • Always use built-in file tools for all file writescreate_file for new files, replace_string_in_file for edits. For gh CLI multi-line bodies: always --body-file <path>. Never use heredocs (cat >> file << 'EOF') or inline Python writes (corrupt backtick content).
  • Always return plans without executing them — read-only by design; create phase structures but do not create, edit, or delete files.
  • Always verify agent names in the fleet catalog before assignment — consult .github/agents/README.md to ensure agent exists.
  • Always flag scripting gaps in plans — design phases with ≤2 interactive repetitions of scriptable tasks; surface automation opportunities.
  • Always specify explicit gate deliverables — vague gates ("done with phase") are insufficient; name exact files, sections, or test results.
  • Always sequence research before implementation — cross-cutting research must be Phase 1 and gate all phases it informs; no parallel-with marking allowed for informing research.

Read the full file on GitHub · 238 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. 2d ago First seen · 238 lines · 28 tokens per session scan A d4344a099103

Subscribe to this mod's changes

Executive Planner is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 28 tokens to every session and 2,325 once invoked, about $0.0001 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.