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 skills add jungjaehoon-lifegamez/MAMA --skill mama-contextgit 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/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 | $0.00023 | $0.00446 |
| Opus 5.5 | $0.00009 | $0.00178 |
| Sonnet 5.5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00045 |
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 25d 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.
What it actually says
MAMA Context
Overview
This skill documents the one hook the MAMA Claude Code plugin ships. The plugin manifest is the
authority for which hooks run. At session start the agent sees the last checkpoint and the newest
active decisions; everything else it pulls when it needs it, with /mama:search <topic> or the MCP
search tool for the full decision, its reasoning, outcome and evolution chain.
Active hook
SessionStart Hook (scripts/sessionstart-hook.js)
- Runs when a Claude Code session starts, resumes or is compacted.
- Installs the plugin's npm dependencies into
${CLAUDE_PLUGIN_DATA}when they are missing or out of date (Claude Code does not install them). - Opens the local memory database and adds the last checkpoint and the five newest active decisions to the session's context. Replaced, retired and contradicted decisions, and records that only amend another, stay out, as recall leaves them out.
- Loads no embedding model.
- Manifest timeout: 180 seconds, for a first dependency install.
No tool or compaction hooks
The plugin registers no PreToolUse, PostToolUse or PreCompact hook (removed 2026-10-01):
- A read hook blocked the first read of each code file to push decisions matched on the file name.
- An edit hook pushed the same reminder after each first edit; recording decisions is in the project instructions.
- A compaction hook's output is shown to the user only and never reaches the compaction.
Configuration boundary
Hook registration lives in packages/claude-code-plugin/.claude-plugin/plugin.json. Feature
activation is controlled by src/core/hook-features.js. To stop the hook entirely, disable the
plugin in Claude Code rather than relying on an undocumented configuration key.
Developer checks
pnpm --dir packages/claude-code-plugin vitest run tests/hooks/sessionstart-hook.test.js
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.
- 25d ago Changed · -38 lines 91b432c646d8
- 1mo ago Changed · -2 lines 097097452f20
- 1mo ago Changed · -152 lines · -5 tokens per session 37ab6b19fe24
- 1mo 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 (14 stars, last pushed 10d ago), licensed MIT. It adds 23 tokens to every session and 446 once invoked, about $0.0001 per session on Opus 5.5. 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
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…
memai-link
Stitch the MemAI relations GRAPH: typed edges between memories (supersedes / relatesto / contradicts / linksto), turning [[wikilinks]] written in a body into real edges, connecting complementary memories that share a domain, and preserving lineage (checkpoint to note, archived to successor). Uses dedupscan to find…
memai-memory
How to use the MemAI MCP server (long-term agent memory: one ACID SQLite store, BM25 keyword search) — which tool family to call when: pulse/mustread/search/recall/listbydomain/listrecent/ listdomains/getmemory to read; note, reasoning, antipattern, checkpoint, task, diagram to write…