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 agentmods add commands/cdeust/ai-architect-mcp-codebase/savegit clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWhat 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 | $0.00000 | $0.00231 |
| Opus 5 | $0.00000 | $0.00115 |
| Sonnet 5 | $0.00000 | $0.00046 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
save 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 2d 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
Save Session Context
Save the current session's context for future recall.
Instructions
-
Summarize the current session: decisions made, files changed, open questions, difficulty-book state.
-
Session state is a block, not an archival fact (zetetic-team-subagents memory/contract.md §8b). Write the summary to the scoped working-state block via
memory-tool.sh rethink /memories/<scope>/checkpoint.md(usecreatefor the first checkpoint); the sync drainer replicates it to Cortex taggedmemory-replica. Do NOT callcortex:rememberfor the session summary itself. -
If the session produced self-contained WHY-level facts (decision + rationale, rejected approach + root cause, lesson), store each via
cortex:rememberwithtags: ["archival", "<project-name>", ...]ANDagent_topic. Be selective. -
Also save locally:
tools/session-store.sh save "<summary>" -
Confirm to the user what was saved (block path + number of archival entries, if any).
$ARGUMENTS
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.
- 2d ago First seen · 18 lines · 0 tokens per session scan A fd95f1a37c35
save is a command published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 231 tokens. 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 commands, from other repositories
learn-architecture
Learn an architecture or design topic — theory, the Pythonic way, and how it applies in your code.
Generate Phase 3
Generate Phase 3 Demo & Learning files (10 files + README) with v2.0 spec.
harness-onboarding
Generate a human-readable onboarding document from HARNESS.md, AGENTS.md, and REFLECTIONLOG.md — a friendly guide for new team members.
ome-evolve
Analyze local memory for learning and skill candidates.
doc-generate
You are a documentation expert specializing in creating comprehensive, maintainable documentation from code.
start-1
Claude Code 를 처음 쓰는 PM 이 "설치 → 도구 지도 이해 → CLAUDE.md 로 맥락 주기" 까지 직접 손으로 해보며 익히도록, 한 번에 한 단계씩 끌고 간다.