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 Emasoft/ai-maestro-architect-agent --skill amaa-session-memorygit clone --depth 1 https://github.com/Emasoft/ai-maestro-architect-agentWrote 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/emasoft/ai-maestro-architect-agent/amaa-session-memory)<a href="https://agentmods.dev/skills/emasoft/ai-maestro-architect-agent/amaa-session-memory"><img src="https://agentmods.dev/badge/skills/emasoft/ai-maestro-architect-agent/amaa-session-memory/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/emasoft/ai-maestro-architect-agent/amaa-session-memory"><img src="https://agentmods.dev/badge/skills/emasoft/ai-maestro-architect-agent/amaa-session-memory.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 | $0.00036 | $0.00817 |
| Opus 5 | $0.00018 | $0.00409 |
| Sonnet 5 | $0.00007 | $0.00163 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
amaa-session-memory 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 9d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Memory Skill
Overview
This skill defines how the Architect agent (AMAA) handles session memory and context persistence. Session memory ensures that architecture decisions, design patterns, technology choices, and discovered constraints survive across multiple sessions, preventing loss of critical design context and enabling seamless session continuity.
Prerequisites
- Write access to design output directories (
docs_dev/design/,.claude/) - Understanding of AMAA role responsibilities (see plugin
docs/ROLE_BOUNDARIES.md) - Familiarity with session state files and design index formats
Instructions
- Session Start -- Check for existing session state at
.claude/amaa-session-state.local.mdand load the design index fromdocs_dev/design/index.json - During Work -- Persist decisions, patterns, constraints, and questions as discovered
- Session End -- Create handoff document if context window is near limit or session is ending
- Session Resume -- Load session state and latest handoff document to restore context
Checklist
Copy this checklist and track your progress:
- Load session state and design index on start
- Persist decisions, patterns, constraints as discovered
- Create handoff document when session ends
Examples
AMAA: Loading session state...
Found 4 decisions, 6 constraints, 2 open questions.
Active design: design-payments-xyz789 (architecture phase)
Next action: Resolve OQ-002 (Payment processor selection)
Error Handling
| Error | Cause | Solution |
|---|---|---|
| Session state not found | First session or file deleted | Initialize new session state file |
| Design index corrupted | Manual edit or system error | Regenerate index from decision files |
| Handoff document incomplete | Interrupted creation | Re-run handoff creation procedure |
Output
| Output Type | Location |
|---|---|
| Architecture Decisions | docs_dev/design/decisions/ADR-NNN-*.md |
| Session State | .claude/amaa-session-state.local.md |
| Design Index | docs_dev/design/index.json |
| Handoff Documents | docs_dev/design/handoffs/handoff-{timestamp}.md |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 1.7 KB
- references/handoff-procedures.md 3.1 KB
- references/memory-categories-and-triggers.md 4.9 KB
- references/op-create-handoff.md 5.9 KB
- references/op-load-session-state.md 5.8 KB
- references/op-record-constraint.md 5.8 KB
- references/op-record-decision.md 5.5 KB
- references/op-record-open-question.md 6.3 KB
- references/op-record-pattern.md 5.0 KB
- references/op-record-stack-choice.md 5.1 KB
- references/op-resume-from-handoff.md 6.3 KB
- references/record-keeping-formats.md 22 KB
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.
- 9d ago First seen · 79 lines · 36 tokens per session scan A 286a280d108e
amaa-session-memory is a skill published in the GitHub repository Emasoft/ai-maestro-architect-agent (2 stars, last pushed 10d ago), licensed MIT. It adds 36 tokens to every session and 817 once invoked, about $0.0002 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
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…
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.