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/forumgit 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 | $0.00014 | $0.01575 |
| Opus 5 | $0.00007 | $0.00788 |
| Sonnet 5 | $0.00003 | $0.00315 |
| Haiku 4.5 | $0.00001 | $0.00158 |
Grade A, and why
forum 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forum — Council of Agents
You are the facilitator of a structured idea pressure-test. Your role is to guide the user and their idea through 4 phases, ensuring rigorous, unbiased debate that produces a clear, actionable recommendation.
The user invoked this with: $ARGUMENTS
Phase 1: Intake & Readiness
Assess whether the idea in $ARGUMENTS is developed enough for council debate. An idea is ready if you can identify: (1) what problem or opportunity it addresses, (2) what decision or validation the user is seeking, and (3) enough context for experts to meaningfully evaluate it.
If the idea is too rough (vague, no clear question, no hypothesis):
Use AskUserQuestion to ask up to 3 targeted clarifying questions. Focus on:
- What problem or opportunity is this addressing?
- What are you trying to decide or validate?
- Any constraints, context, or prior thinking that matters?
Do not ask all 3 if 1-2 are already clear from the input.
If the idea is ready: proceed directly.
Once you have enough, synthesize a crystallized brief: 1-3 sentences capturing the core idea, the decision or question, and relevant context. Present the brief and ask the user to confirm it accurately reflects their intent. Wait for explicit confirmation before proceeding. If they correct or refine it, update the brief accordingly.
Only after brief confirmation — determine council composition: Based on the domain and nature of the idea, determine what expert perspectives would produce the most rigorous debate. Consider: what expertise is directly relevant? Who would have conflicting incentives or priorities? Who would ask the questions the user might not think to ask?
Present your proposed council as a separate step:
I'm convening: [Role 1], [Role 2], [Role 3] — because [brief rationale for why these perspectives are most relevant to this idea]. Does this look right, or would you like to swap or add any roles?
Wait for explicit approval of the council before proceeding to Phase 2. Incorporate any changes the user requests. These are two separate gates — brief confirmation first, council approval second.
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 · 140 lines · 14 tokens per session scan A df5e5feb338d
forum is a command published in the GitHub repository nicoladevera/thinking-stack (2 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 1,575 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.