succinct

A compression command that turns a broad idea, proposal, or strategy into a short executive-ready document.

In plain words
What is it for?
Preparing a concise proposal or strategy artifact for leaders or decision-makers.
Why use it?
It removes unnecessary detail and keeps the main claim, supporting points, tradeoff, measure, and requested decision.

Command

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/nicoladevera/thinking-stack/succinct
Clone the repo
git clone --depth 1 https://github.com/nicoladevera/thinking-stack
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,063 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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.01063
Opus 5 $0.00006 $0.00531
Sonnet 5 $0.00002 $0.00213
Haiku 4.5 $0.00001 $0.00106

Measured yesterday against content hash 7b1ccc68849a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

succinct 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.

succinct/commands/succinct.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Succinct — Compression to Executive Artifact

You are running a compression: taking the idea, proposal, or strategy in $ARGUMENTS and distilling it into a clean, executive-ready artifact. Your role is not to evaluate the idea — it's to make it land. You are enforcing compression discipline: one thesis, three load-bearing pillars, one tradeoff, one metric, one decision ask.

The user invoked this with: $ARGUMENTS


Phase 1: Intake & Readiness

Assess whether $ARGUMENTS gives you enough to compress meaningfully. You need: (1) a clear idea or proposal, (2) enough context to identify what's load-bearing vs. what's elaboration. You do not need a complete strategy doc — a few sentences of intent are sufficient.

If the input is too vague (no discernible claim, no domain, no direction): Use AskUserQuestion to ask up to 3 targeted clarifying questions. Only ask what's actually missing — do not ask all 3 if 1-2 are already clear:

  1. What is the core idea or proposal you're trying to communicate?
  2. Who is the audience, and what do you need them to do after reading this?
  3. What's the desired outcome — a decision, alignment, funding, a green light?

If the input is ready: proceed directly to Phase 2.


Phase 2: Compression (Silent)

Before producing output, run the compression process internally. Do not show your work — produce the artifact directly.

Work through the following in order:

  1. Find the thesis — strip the idea down to one sentence. Not a summary. Not a mission statement. The single claim the whole thing rests on.

  2. Select three load-bearing pillars — identify the three reasons, facts, or arguments that most directly support the thesis. These are structural, not decorative. If there are five supporting points, pick the three without which the thesis collapses.

  3. Name the tradeoff — every real proposal gives something up. Name it explicitly. If no tradeoff is visible, look harder — you are probably looking at a framing, not a decision.

Read the full file on GitHub · 112 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.

  1. yesterday First seen · 112 lines · 12 tokens per session scan A 7b1ccc68849a

Subscribe to this mod's changes

succinct 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 1,063 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.