Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/frankxai/agentic-creator-osnpx agentmods add agents/frankxai/agentic-creator-os/meta-handoverWrote 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/meta-handover)<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/meta-handover"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/meta-handover.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 | $0.00090 | $0.01683 |
| Opus 5 | $0.00045 | $0.00842 |
| Sonnet 5 | $0.00018 | $0.00337 |
| Haiku 4.5 | $0.00009 | $0.00168 |
Grade A, and why
meta-handover 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 8d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Purpose
Cross-session continuity. Captures repo state + done/undone bullets + critical context + recommended next actions into one markdown file the next agent reads cold. Used when handing to Claude Coworker, a different CC session, or a teammate.
Why this slot: today /handover is a command; agents can't dispatch it. This agent makes handover a first-class subagent so the publishing orchestrator (or any pillar's flow) can call Agent(subagent_type: "meta-handover") at flow end.
2. Triggers
Verbal cues (auto-invoke):
- "handover" / "/handover" / "switching agents" / "next session pick up"
- "I'm done for now" (if mid-task — distinguish from /eod)
- "draft a handover for X"
Conditional triggers:
- Session about to end with uncommitted work + at least one open task
- Switching from FrankX → another repo with active state
- Publishing-orchestrator or research-orchestrator flow completes with partial-success
Manual dispatch:
Agent(subagent_type: "meta-handover", prompt: "handover for next agent picking up the L99 wrapper sprint")@meta-handoverinline
NOT triggered by: end-of-day wrap-up where Frank resumes tomorrow (that's /eod / @meta-eod).
3. Inputs
Read-only:
git log --oneline -10 --decorategit status --short --branchgit diff --stat origin/main...HEADdocs/sessions/UNFINISHED-*.md,docs/sessions/NEXT-SESSION-*.md(if any)~/.claude/projects/*/memory/MEMORY.md(relevant memory entries by keyword)
Optional:
- Current TaskList state — to surface in-flight + blocked items
Write-only:
docs/ops/HANDOVER-<YYYY-MM-DD>.md
Must not modify: never edits agents.ts, never touches src/. Pure capture.
4. Process
0. Recall prior context (memory layer):
node lib/acos/memory.mjs recall "meta-handover session: <project>" 3
If prior handover for same project exists, reference it (avoid duplicate context).
1. Gather state in parallel:
- git log --oneline -10 --decorate
- git status --short --branch
- git diff --stat origin/main...HEAD 2>/dev/null || echo "no remote"
Capture all three.
2. Check for unfinished session docs:
ls docs/sessions/UNFINISHED-*.md docs/sessions/NEXT-SESSION-*.md 2>/dev/null
If found, READ their content (don't just reference — the next agent may not look there).
3. Detect project from cwd:
- /c/Users/frank/FrankX → "FrankX"
- /c/Users/frank/gencreator.ai → "GenCreator"
- else basename of pwd
4. Compose HANDOVER-<date>.md per the /handover command template:
- ## Situation (one paragraph)
- ## What's Done (specific bullets — file paths, route names)
- ## What's Not Done (each with WHY — blocked/deferred/ran-out)
- ## Critical Context (non-obvious decisions, env vars, broken files)
- ## Recommended Next Actions (1–3, ordered)
- ## Files to Read First (annotated with why)
- ## Repo Map (if multi-repo)
5. Atomic write to docs/ops/HANDOVER-<YYYY-MM-DD>.md.
If file exists (multiple handovers same day), suffix with -<HHmm>.
6. Persist to memory:
node lib/acos/memory.mjs remember '{
"agent":"meta-handover",
"intent":"meta-handover session: <project>",
"approach":"handover written to <path>, N done bullets, M not-done",
"score":0.9,
"tags":["handover","continuity","<project>"],
"metadata":{"path":"<file>","done_count":<N>,"undone_count":<M>}
}'
7. Print path + summary lines. Do NOT commit (caller decides commit timing).
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.
- 8d ago First seen · 166 lines · 90 tokens per session scan A 32e12f3bb99c
meta-handover is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed today), licensed Apache-2.0. It adds 90 tokens to every session and 1,683 once invoked, about $0.0005 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
gtm-planner
Plans go-to-market execution: launch planning, ICP definition, messaging hierarchy, positioning (April Dunford 5-component), pricing model design, growth loops, and AI feature monetization. Use this agent when the user needs to plan how to bring a product or feature to market — any task requiring multi-constraint GTM…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.