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/nicoladevera/thinking-stack/vaultgit clone --depth 1 https://github.com/nicoladevera/thinking-stackWhat 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 | $0.00012 | $0.03235 |
| Opus 5 | $0.00006 | $0.01618 |
| Sonnet 5 | $0.00002 | $0.00647 |
| Haiku 4.5 | $0.00001 | $0.00324 |
Grade A, and why
vault 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 yesterday.
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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault — Session Capture and Canonization
You are running a vault: a capture operation that promotes the thinking work done in this conversation into a structured, versioned personal archive. Your role is not to think — it is to preserve, canonize, and index. You read what happened, confirm it with the user, gather the metadata needed to make it retrievable and meaningful over time, and write two artifacts: a human-readable Markdown document and a machine-readable JSONL index entry.
Vault is an output layer, not a reasoning tool. Do not add analysis, critique, or new thinking. Your job is accurate capture and structured preservation.
VAULT_PATH: ~/Documents/vault
Phase 1: Scan and Confirm
Read back through the full conversation context. Identify all thinking-stack commands that were used (blindspot, forum, premortem, horizon, conviction, succinct), the core topic, and whether this is a structured or freeform session.
If a single thinking command was used:
Use AskUserQuestion to confirm:
I found a /[command] session on [topic]. Is this what you want to vault?
If multiple thinking commands were used in the same conversation:
Use AskUserQuestion to present each individually and ask which to vault now:
I found [N] thinking sessions in this conversation:
- /[command1] — [brief topic description]
- /[command2] — [brief topic description]
Which would you like to vault? Run /vault again after to capture the other.
If no thinking commands were used (freeform session):
Use AskUserQuestion to confirm:
I found a freeform conversation about [topic]. Is this what you want to vault?
Wait for explicit confirmation before proceeding. If the user corrects or narrows the scope, note the change and proceed with the adjusted scope.
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.
- yesterday First seen · 327 lines · 12 tokens per session scan A 4cba7f0cde5a
vault is a command published in the GitHub repository nicoladevera/thinking-stack (2 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 3,235 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 2026-08-31.
Other commands, from other repositories
change
Entry point for any change request. Orchestrates the planner-routing pipeline (cm-planner → executor → reviewer → conventions-audit → test-author → commit). Use for any work that touches code or docs.
tree
Show file tree with sync status indicators showing which files are indexed, modified, new, or deleted.
adr
You are helping create a new ADR (Architecture Decision Record). This is a conversational process — you interview the user about the decision, then create a filled-in record. ADRs capture the WHY behind technical choices so future-you understands the reasoning.
routine
Execute one maintenance routine defined in scv/routines/ .md (task + guardrails + exit-criteria contract), or list defined routines. SCV never schedules — pair with host features like /loop or cron yourself. Use whenever the user asks to run a recurring maintenance task, or asks what routines exist — not only when…
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.