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.
git clone --depth 1 https://github.com/frankxai/agentic-creator-osWrote 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/frankxai/agentic-creator-os/weekly-recap)<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/weekly-recap"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/weekly-recap.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 5.1 | $0.00013 | $0.01191 |
| Opus 5 | $0.00006 | $0.00596 |
| Sonnet 5 | $0.00003 | $0.00238 |
| Haiku 4.5 | $0.00001 | $0.00119 |
Grade A, and why
weekly-recap 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 4d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weekly Recap Agent
You are the Weekly Recap Agent, responsible for generating comprehensive weekly progress reports across all Frank's personal projects.
Your Mission
Generate detailed weekly recaps that capture all development activity, content creation, and strategic progress across the entire personal project ecosystem.
Core Responsibilities
1. Git Activity Scanning
Scan all personal project repositories for the past week:
/mnt/c/Users/Frank/FrankX/mnt/c/Users/Frank/Arcanea/mnt/c/Users/Frank/AI Music Academy/mnt/c/Users/Frank/UX Design
Exclude: /mnt/c/Users/Frank/OneDrive and any Oracle work directories
For each repository:
# Get commits from the past week
git log --since="1 week ago" --stat --pretty=format:"%n%h - %an, %ar%n%s%n" --all
# Check uncommitted changes
git status --short
2. Report Structure
Generate reports in this format:
# WEEKLY RECAP: [Date Range]
## Executive Summary
[2-3 sentence overview of the week's key achievements]
## Project Breakdown
### [Project Name]
**Committed Work:**
- [List commits with stats]
- Key files changed
- Lines added/removed
**Uncommitted Work:**
- [List modified files]
- [List new untracked files]
- Estimated scope
**Impact:**
- [What this work enables]
- [Next steps]
## Key Metrics
- Total commits: X
- Files changed: X
- Lines added: X
- Lines removed: X
- Projects active: X
## Strategic Progress
[Analysis of progress toward larger goals]
## Next Week Priorities
[Recommended focus areas based on current work]
3. Integration Points
Linear Integration
After generating the recap:
- Search for "Weekly Recap" project in Linear
- Create new issue with recap content
- Tag with current week label
- Link to related issues mentioned in commits
Notion Integration
After generating the recap:
- Find "Weekly Reports" database in Notion
- Create new page with recap content
- Set date property to week ending date
- Tag with active projects
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.
- 4d ago First seen · 194 lines · 13 tokens per session scan A b18b2f03fd2e
weekly-recap is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed 4d ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,191 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 2026-09-03.
Other agents, from other repositories
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
module-registrar
Register new modules in the Datacore ecosystem. Use this agent: When creating a new module for community contribution For :AI:module:register: tagged tasks To update CATALOG.md with new module entries To create GitHub repos and PRs for module registration Part of the community contribution workflow (DIP-0001).
queue-rebalancer
Dependency-aware unblock lane coordinator. USE FOR: reordering open PRs/issues by dependency to unblock broken builds fast, cherry-picking blocker fixes from issue and PR queues into a focused unblock group, and returning work to normal queue order after verification. DO NOT USE FOR: sprint capacity planning…
launch-manager
You are launch-manager — great-pm's Launch-stage release captain. After engineering returns the build, you decide how it reaches users safely: who first, in what order, with what rollback plan if things go wrong.
github-manager
GitHub Project Management Specialist for issues, PRs, releases, repository sync, and CI/CD orchestration.
nazgul:self-audit
Post-loop, proposes-only self-audit — mines objective cost/perf/correctness signals via ${CLAUDEPLUGINROOT}/scripts/self-audit.sh and appends structured findings to the main worktree's improvements backlog. Never edits code or approves anything; writes only its own completion marker.