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/jungjaehoon-lifegamez/MAMAWrote 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/commands/jungjaehoon-lifegamez/mama/checkpoint)<a href="https://agentmods.dev/commands/jungjaehoon-lifegamez/mama/checkpoint"><img src="https://agentmods.dev/badge/commands/jungjaehoon-lifegamez/mama/checkpoint/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.
<a href="https://agentmods.dev/commands/jungjaehoon-lifegamez/mama/checkpoint"><img src="https://agentmods.dev/badge/commands/jungjaehoon-lifegamez/mama/checkpoint.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00009 | $0.01009 |
| Opus 5 | $0.00005 | $0.00504 |
| Sonnet 5 | $0.00002 | $0.00202 |
| Haiku 4.5 | $0.00001 | $0.00101 |
Grade A, and why
checkpoint scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Quick checks: npm test ..., curl http://localhost:3000/health How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Session Checkpoint (with Self-Verification)
You are helping the user save the current session state to MAMA memory.
User Arguments: $ARGUMENTS
💬 Checkpoint Writing Guide
A checkpoint is a handoff to the next AI. Be candid so the next person can resume fast.
🤔 Ask yourself before writing
- Goal & Progress? What was today’s goal and where did you stop?
- Evidence? What did you verify? Mark status as
Verified | Not run | Assumed. - Unfinished/Risks? What’s incomplete, blocked, or risky?
- Next Agent Briefing? What quick health/start commands should they run first?
It doesn’t have to be perfect—state what’s missing.
😊 Good pattern
# 🎯 Goal & Progress
- Goal: [Session goal]
- Progress: [What you did, where you stopped, why unfinished]
# ✅ Evidence & Verification
- File `path/to/file.js` — Status: Verified (cite test/log/line)
- Command `npm test ...` — Status: Not run (reason: time)
- Log `[MAMA MCP] ...` — Status: Assumed (reused log)
# ⏳ Unfinished & Risks
- Remaining work: ...
- Tests/health checks not run: ... (reason)
- Risks/unknowns: ...
# 🚦 Next Agent Briefing
- DoD: [Definition of Done for next session]
- Quick checks: npm test ..., curl http://localhost:3000/health
- Constraints: [Constraints/cautions]
🔧 Trust lift (after resume): run 1-2 quick checks above, sample-verify one claim per section (file/log/command), and relabel Assumed → Verified/Not run before re-saving.
Step 4: Call MCP Tool
mcp__plugin_mama_mama__save({
type: 'checkpoint',
summary: '...', // Use the Goal/Evidence/Unfinished format above
open_files: ['file1.js', 'file2.md'],
next_steps: 'DoD + quick checks (e.g., npm test ..., curl ...)',
});
😅 This makes handoff hard
Vague:
- "Epic 3 done!" → unclear what’s done
Better:
- "Epic 3: Story 3.1-3.2 done; 3.3 coded but untested"
Instead of “all done”:
- "proposeLink implemented (file.js:100), tests not written"
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.
- 10d ago First seen · 125 lines · 9 tokens per session scan A 9a3a2c261a74
checkpoint is a command published in the GitHub repository jungjaehoon-lifegamez/MAMA (13 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 1,009 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
meeting-notes
Summarize a meeting transcript into structured notes with decisions, action items, and follow-ups.
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
acos
The single command you need. ACOS auto-routes everything.
acos-checkpoint
Create checkpoints before risky operations. Rollback if things go wrong.
ops
Weekly operations loop — triage the inquiry inbox, advance the CRM pipeline, sweep open PRs across repos, and surface the content plan. Loads the ops skill.
takeoff
Create, resume, or clear a session hand-off baton (one per work line).