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/jungjaehoon-lifegamez/MAMAnpx agentmods add skills/jungjaehoon-lifegamez/mama/mama-contextWrote 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/jungjaehoon-lifegamez/mama/mama-context)<a href="https://agentmods.dev/skills/jungjaehoon-lifegamez/mama/mama-context"><img src="https://agentmods.dev/badge/skills/jungjaehoon-lifegamez/mama/mama-context/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/skills/jungjaehoon-lifegamez/mama/mama-context"><img src="https://agentmods.dev/badge/skills/jungjaehoon-lifegamez/mama/mama-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 35 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00028 | $0.01630 |
| Opus 5 | $0.00014 | $0.00815 |
| Sonnet 5 | $0.00006 | $0.00326 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
mama-context 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MAMA Context - Auto-Injection Skill
Overview
This skill provides automatic background context injection using MAMA's hook system. It runs silently and surfaces relevant past decisions via the UserPromptSubmit hook (~150ms latency with HTTP embedding server).
Philosophy: Gentle hints, not intrusive walls of text. Claude sees topic + time, decides if relevant.
How It Works
The skill uses a multi-hook system for comprehensive context injection:
UserPromptSubmit Hook (active, ~150ms — no plugin-side script; handled by Claude Code host)
- Triggers: On every user message submission
- Purpose: Inject relevant decisions as context before Claude responds
- Latency: ~150ms (HTTP embedding server keeps model in memory)
- Token budget: 40 tokens (teaser format)
SessionStart Hook (scripts/sessionstart-hook.js)
- Triggers: Once per session
- Purpose: Initialize MAMA, pre-warm embedding model
- Timeout: 15s
PreToolUse Hook (scripts/pretooluse-hook.js) - disabled (script retained)
- Previously: Injected contracts before Edit/Write operations
- Status: Disabled for performance. Script retained for future use.
PostToolUse Hook (scripts/posttooluse-hook.js) - disabled (script retained)
- Previously: Tracked code changes, suggested decision saves
- Status: Disabled for performance. Script retained for future use.
PreCompact Hook (scripts/precompact-hook.js)
- Triggers: Before context compaction
- Purpose: Preserve unsaved decisions in compacted context
- Timeout: 10s
Teaser Format (40 tokens)
💡 MAMA: 2 related
• authentication_strategy (85%, 3 days ago)
• mesh_detail (78%, 1 week ago)
/mama:search <topic> for details
Why teaser?
- Hooks fire on user messages (UserPromptSubmit) → Must be lightweight
- Claude infers relevance from topic + similarity + time
- Full details available via
/mama:searchif needed - Avoids token bloat (250 tokens → 40 tokens)
Status Transparency
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 · 240 lines · 28 tokens per session scan A 191d4010787a
mama-context is a skill published in the GitHub repository jungjaehoon-lifegamez/MAMA (13 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,630 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 skills, from other repositories
memories-off
A local knowledge-base skill that stores people, projects, notes, and their relationships in Markdown files. It supports long-term memory for an AI assistant.
codemem
Quick reference for all 32 codemem MCP tools. Use when working with the codemem knowledge graph — finding code, traversing relationships, storing memories, or running analysis.
memai-maintenance
Orchestrator of the MemAI MAINTENANCE pass (long-term agent memory). Runs [[memai-checkpoints]], [[memai-distill]], [[memai-confidence]] and [[memai-link]] as one curation pass, owns what none of them covers — the DOMAIN TREE (nested paths, cross-listing, casing), the DIAGRAMS and the store's DECAY (reviewafter) — and…
memai-confidence
Verify a MemAI memory's claims against live facts and set its confidence (unverified | confirmed | contradicted). Checks the anchors a scan already extracted — file:line, symbol, table/column, domain, URL — against today's source, promotes or demotes each memory, stages a reword for a detail that drifted, and pushes…
memai-checkpoints
The lifecycle of MemAI CHECKPOINTS: deciding which bearing is still current and which one is superseded, archiving the checkpoint of work that is closed or an intra-session trail that a newer one already covers, keeping the single bearing a live effort still needs, correcting a fact in a kept checkpoint that has gone…
memai-distill
Distill and MOVE knowledge between MemAI types: pull what is durable out of one checkpoint (or several) into a note/reasoning/antipattern, change a memory's type (checkpoint→note when the content is timeless), and merge near-duplicates. Use when the user asks to "distill memory", "turn a checkpoint into a note", "move…