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 skills/benrben/mpga/handoffnpx skills add benrben/MPGA --skill handoffgit clone --depth 1 https://github.com/benrben/MPGAWrote 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/skills/benrben/mpga/handoff)<a href="https://agentmods.dev/skills/benrben/mpga/handoff"><img src="https://agentmods.dev/badge/skills/benrben/mpga/handoff.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 | $0.00014 | $0.01021 |
| Opus 5 | $0.00007 | $0.00511 |
| Sonnet 5 | $0.00003 | $0.00204 |
| Haiku 4.5 | $0.00001 | $0.00102 |
Grade A, and why
mpga-handoff 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
handoff
Trigger: Context window getting full or user requests handoff.
Protocol
-
Check context budget:
mpga session budget -
Capture git state:
# Current branch git rev-parse --abbrev-ref HEAD # Last commit hash + message git log -1 --oneline # Dirty files (staged + unstaged + untracked) git status --short # Stash count git stash list | wc -l -
Capture task state from the board:
mpga board showIdentify: current task ID, TDD stage (red/green/blue), what tests pass, what tests fail.
-
Compose the structured handoff document using the Handoff Template below. Fill in every section — no blanks, no shortcuts.
-
Save handoff document:
mpga session handoff --accomplished "<summary>" -
Log the session:
mpga session log "<brief description of work done>" -
Output the completed handoff template as a fenced markdown block so the user can copy-paste it into a new session.
-
Tell the user:
- The handoff file location
- How to resume: load handoff + INDEX.md + relevant scopes
- What the next action is — exactly what to do next.
Handoff Template
Output this template with all placeholders filled in. Every section is mandatory.
# Session Handoff — {{DATE}}
## Git State
| Field | Value |
|-------|-------|
| **Branch** | `{{BRANCH}}` |
| **Last commit** | `{{SHORT_HASH}} {{COMMIT_MSG}}` |
| **Dirty files** | {{DIRTY_COUNT}} files (see list below) |
| **Stash count** | {{STASH_COUNT}} |
### Dirty file list
```
{{GIT_STATUS_SHORT_OUTPUT}}
```
## Task State
| Field | Value |
|-------|-------|
| **Current task** | `{{TASK_ID}}` — {{TASK_TITLE}} |
| **TDD stage** | {{red / green / blue / n/a}} |
| **Passing tests** | {{LIST_OR_COUNT}} |
| **Failing tests** | {{LIST_OR_COUNT_OR_NONE}} |
| **Milestone** | {{MILESTONE_ID_OR_NONE}} |
## Context Summary
### What was being worked on
<!-- 2-4 sentences describing the current focus area -->
{{WORK_SUMMARY}}
### Key decisions made
<!-- Bullet list of decisions WITH rationale -->
{{DECISIONS}}
### Blockers encountered
<!-- Bullet list, or "None" if clear -->
{{BLOCKERS}}
## Next Steps
<!-- Numbered list — the FIRST item is what the next session should do IMMEDIATELY -->
1. {{IMMEDIATE_NEXT_ACTION}}
2. {{FOLLOW_UP_ACTION}}
3. {{FURTHER_ACTION}}
## Open Questions
<!-- Anything unresolved that needs human input. "None" if clear. -->
{{OPEN_QUESTIONS}}
---
### Resume instructions
```
To resume in a new session:
1. Paste this entire handoff document into the new session
2. Load index: cat MPGA/INDEX.md
3. Load relevant scope: cat MPGA/scopes/<scope>.md
4. Run: /mpga:next
```
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 · 153 lines · 14 tokens per session scan A e6dc9efde70c
mpga-handoff is a skill published in the GitHub repository benrben/MPGA (5 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 1,021 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.
Other skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…