ai-executive-assistant: Skill for Codex

.agents/skills/source-command-ea-weekly-retro/SKILL.md

source-command-ea-weekly-retro is a skill for Codex from cosmo-autom8s/ai-executive-assistant. It costs 20 tokens per session (1,316 once invoked), scanned A, original, MIT.

A Friday review that examines an executive assistant's weekly plans, progress notes, current status, and monthly goals.

In plain words
What is it for?
It gathers the week's planning and activity files, then reports completion, recurring patterns, successes, misses, and practical improvements.
Why use it?
It helps compare intended outcomes with actual progress and identify patterns that can improve the following week.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions Claude Code; installed under .agents/ (shared by several agents).

This is cosmo-autom8s/ai-executive-assistant's own configuration. It tells Codex how to work on ai-executive-assistant itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-executive-assistant configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cosmo-autom8s/ai-executive-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cosmo-autom8s/ai-executive-assistant/main/.agents/skills/source-command-ea-weekly-retro/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cosmo-autom8s/ai-executive-assistant

Made for: Codex.

Wrote 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.

agentmods badge for source-command-ea-weekly-retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/cosmo-autom8s/ai-executive-assistant/source-command-ea-weekly-retro/github.svg)](https://agentmods.dev/skills/cosmo-autom8s/ai-executive-assistant/source-command-ea-weekly-retro)
Your own site
<a href="https://agentmods.dev/skills/cosmo-autom8s/ai-executive-assistant/source-command-ea-weekly-retro"><img src="https://agentmods.dev/badge/skills/cosmo-autom8s/ai-executive-assistant/source-command-ea-weekly-retro/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for source-command-ea-weekly-retro

Your own site · 80×15
<a href="https://agentmods.dev/skills/cosmo-autom8s/ai-executive-assistant/source-command-ea-weekly-retro"><img src="https://agentmods.dev/badge/skills/cosmo-autom8s/ai-executive-assistant/source-command-ea-weekly-retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00020 $0.01316
Opus 5 $0.00010 $0.00658
Sonnet 5 $0.00004 $0.00263
Haiku 4.5 $0.00002 $0.00132

Measured 10d ago against content hash 4ddcd0e6c235, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

source-command-ea-weekly-retro 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 10d 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.

.agents/skills/source-command-ea-weekly-retro/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

source-command-ea-weekly-retro

Use this skill when the user asks to run the migrated source command ea-weekly-retro.

Command Template

Weekly Retro

Read the EA profile for the user's profile, connected tools, and preferences. The profile location is agent-specific (e.g., ~/.claude/ea-profile.md for Claude Code, ~/.codex/ea-profile.md for Codex). Check the data_dir field in the profile for the EA context directory. If not set, default to ~/.codex/ea-context/.

You are the user's Executive Assistant. This is the Friday look-back. Your job is to help learn from the week — not just report numbers, but surface patterns and make next week better.

Adopt the communication style from the user's profile. Default: honest, reflective, no sugarcoating. Highlight what went well AND be direct about patterns that aren't working.

Phase 1: INTAKE — Gather Data

Context Files

  1. Read <data_dir>/weekly-plan.md — what were the planned outcomes and sprint goal?
  2. Read <data_dir>/velocity.md — daily entries from this week
  3. Read <data_dir>/today.md — current day's status
  4. Read <data_dir>/monthly-goals.md — which monthly goals were in play?

Tasks

Pull task data from the user's task management tool (if connected).

  • Read <data_dir>/task-cache.md first. If cache is < 12 hours old, use cached data.
  • Get all tasks to categorize: completed this week, moved, dropped, new (unplanned), and carry-overs.
  • If no task tool is configured, rely on context files and conversation.

Knowledge Base

Check the user's knowledge base for daily notes from this week (Monday through today).

  • Look for: energy levels, mood signals, what felt good vs. draining.
  • If no knowledge base is configured, skip.

Phase 2: ANALYZE — Find the Patterns

Velocity Calculation

  • Planned: How many tasks were on the weekly plan?
  • Completed: How many reached Done status?
  • Completion rate: Completed / Planned (as percentage)
  • Overcommit score: Planned / Completed (>1.5 means chronic overcommitting)
  • Moved: How many tasks got pushed to later dates?
  • Dropped: How many were removed entirely?
  • New (unplanned): How many tasks appeared mid-week?

Read the full file on GitHub · 140 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. 10d ago First seen · 140 lines · 20 tokens per session scan A 4ddcd0e6c235

Subscribe to this mod's changes

source-command-ea-weekly-retro is a skill published in the GitHub repository cosmo-autom8s/ai-executive-assistant (3 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 1,316 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.