A command that manages a research session: a saved workspace for a question, hypotheses, evidence, and notes. It can start, resume, or close that session.

Use it to create research files and a notebook, reload an earlier investigation, inspect its progress, or close it with a structured summary.

It keeps research work organized across multiple working sessions so earlier questions, findings, and notes are not lost.

session — Command by cdeust

Install

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.

agentmods

npx agentmods add commands/cdeust/ai-architect-mcp-codebase/session

Clone the repo

git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebase

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 595 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00595
Opus 5	$0.00000	$0.00298
Sonnet 5	$0.00000	$0.00119
Haiku 4.5	$0.00000	$0.00060

Measured 2d ago against content hash 407faa9e3931, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session 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.

.claude/commands/research/session.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Session

Start, resume, or close a research session. Manages research context: question, hypotheses, evidence state, and lab notebook.

Instructions

Parse $ARGUMENTS for the subcommand:
- session start "<research question>" — create a new session
- session resume — load previous session state
- session close — produce summary and archive
Start: Run tools/research-session-manager.sh start "<question>". This creates research/, initializes NOTEBOOK.md, and writes .session.json. Confirm the research question back to the user and suggest formulating initial hypotheses with session hypothesis add.
Resume: Run tools/research-session-manager.sh resume. Display the current research question, active hypotheses, and notebook entry count. If Cortex is available, call cortex:recall with the research question to load prior context. Summarize what was found and suggest next steps.
Close: Run tools/research-session-manager.sh status first to show final state. Then run tools/research-session-manager.sh close. Produce a structured summary:
- Research question
- Hypotheses and their final status (confirmed / rejected / open)
- Key findings from notebook entries
- Open questions for future sessions
Persist per zetetic-team-subagents memory/contract.md §8b — two endpoints, never one flat remember:
- State (question status, hypothesis ledger, open questions): memory-tool.sh rethink /memories/research/checkpoint.md "<structured summary>" (block verb; the sync drainer replicates it tagged memory-replica).
- Facts (confirmed/rejected hypotheses with evidence, lessons): one cortex:remember per self-contained finding with tags: ["archival", "research", "session-close"] AND agent_topic: "research".
If no subcommand is given, run tools/research-session-manager.sh status to show current state.
For hypothesis management, delegate to:
- tools/research-session-manager.sh hypothesis add "<hypothesis>"
- tools/research-session-manager.sh hypothesis list

Read the full file on GitHub · 41 lines

Changes

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 · 41 lines · 0 tokens per session scan A 407faa9e3931

Subscribe to this mod's changes

session 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 595 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.

Data and AI Databases Research bm25 claude-code claude-code-plugin clean-architecture code-graph code-intelligence

session

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Research Session

Instructions

What this file has done since we first saw it

Other commands, from other repositories

brooks-audit

brooks-health

daily-standup

deploy

fix-issue

simplify