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/decision)<a href="https://agentmods.dev/commands/jungjaehoon-lifegamez/mama/decision"><img src="https://agentmods.dev/badge/commands/jungjaehoon-lifegamez/mama/decision/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/decision"><img src="https://agentmods.dev/badge/commands/jungjaehoon-lifegamez/mama/decision.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 | $0.00012 | $0.00649 |
| Opus 5 | $0.00006 | $0.00324 |
| Sonnet 5 | $0.00002 | $0.00130 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
decision 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 11d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Decision to MAMA Memory
You are helping the user save a decision to MAMA (Memory-Augmented MCP Assistant).
User Arguments: $ARGUMENTS
Instructions
-
Parse the user's input to extract:
topic(required): Decision topic identifier (e.g., 'auth_strategy', 'database_choice')decision(required): What was decided (e.g., 'Use JWT with refresh tokens')reasoning(required): Why this decision was madeconfidence(optional): 0.0-1.0, default 0.5outcome(optional): 'pending', 'success', 'failure', 'partial', 'superseded', default 'pending'type(optional): 'user_decision' or 'assistant_insight', default 'user_decision'failure_reason(optional): Why this decision failed (if outcome='failure')limitation(optional): Known limitations of this decision
-
Use the MCP tool to save the decision:
- Call
mcp__plugin_mama_mama__savewithtype='decision'and the parsed parameters - The tool will return a decision_id
- Call
-
Format the response as markdown:
✅ Decision Saved Successfully **Decision ID:** `{decision_id}` **Topic:** `{topic}` Search for this decision later: `/mama:search {topic}`
Example Usage
/mama:decision auth_strategy "Use JWT with refresh tokens" "Provides better security than sessions" --confidence=0.9 --outcome=success
Error Handling
If required fields are missing, show this help:
Usage: /mama:decision <topic> <decision> <reasoning> [options]
Required:
topic Decision topic (e.g., 'auth_strategy')
decision What was decided
reasoning Why this decision was made
Optional:
--confidence=N Confidence 0.0-1.0 (default: 0.5)
--outcome=X pending|success|failure|partial|superseded (default: pending)
Examples:
/mama:decision auth "Use JWT" "Better security" --confidence=0.9
/mama:decision database "Use PostgreSQL" "Better for our use case" --outcome=success
Important Notes
- Reasoning is required: Never save a decision without reasoning
- Topic naming: Use lowercase with underscores (e.g., 'mama_architecture')
- Reuse topics: Use the SAME topic for related decisions to create evolution graphs
- Graph connectivity: Supersedes edges created automatically when same topic reused
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.
- 11d ago First seen · 74 lines · 12 tokens per session scan A 25066aa75c1a
decision is a command published in the GitHub repository jungjaehoon-lifegamez/MAMA (13 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 649 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 2026-08-30.
Other commands, from other repositories
rb-refresh
A command that rebuilds RepoBrain's knowledge base for the current workspace. RepoBrain is a tool that keeps searchable project information for an agent.
init-workspace-flow-discovery
Phase 3 Discovery of init-workspace-flow.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
weekly
Weekly memory report — facts learned, procedures, repeated mistakes prevented.
prompts
Work with MCP prompt templates for memory operations.
broadcast
Run broadcast on a distilled Raw — update related existing pages conversationally.