understand

A command for gathering thorough context and clarifying the real problem before discussing solutions.

In plain words
What is it for?
Use it when a request is vague, politically complicated, or likely to hide a different underlying need.
Why use it?
It helps prevent premature fixes by examining assumptions, affected people, constraints, and what success should mean.

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/bjcoombs/ai-native-toolkit/understand
Clone the repo
git clone --depth 1 https://github.com/bjcoombs/ai-native-toolkit
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 435 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 $0.00019 $0.00435
Opus 5 $0.00010 $0.00217
Sonnet 5 $0.00004 $0.00087
Haiku 4.5 $0.00002 $0.00044

Measured 2d ago against content hash 2ee22473f642, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

understand 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.

commands/understand.md · 36 lines

What it actually says

Deep Understanding Mode

Lay groundwork before any solution. Create space for the true need to emerge; understand it fully, unpack complexity without rushing to solve. Reach an intuitive grasp of the core issue.

Disciplines:

  • Strict focus on problem definition - no solution exploration. Reject solution discussions; request reframing when solutions appear in the problem statement.
  • Question assumptions and vague terms with determination; challenge the framing, the scope, and whether the problem needs solving at all.
  • Hold space for ambiguity until clarity emerges; attend to context.
  • Consider what is unnecessary or removable - elimination and simplification are valid.
  • Separate people from problems; look past stated positions to underlying interests; distinguish what people want from why. Reframe positions as shared interests; challenge either/or thinking; suggest objective criteria.

Core questions:

  • What do we mean by [key terms]?
  • What explicit and implicit needs exist?
  • Who are the stakeholders, and what interests sit behind their positions?
  • What defines success? What objective criteria would all stakeholders accept?
  • What constraints and cultural/contextual factors matter?
  • What is the gap between current and ideal state?
  • What knowledge gaps need investigation?
  • Could elimination serve better than a solution? What happens if we do nothing? What could be removed entirely?

Understanding is complete when: core terms are defined; explicit and implicit needs surfaced; scope bounded; success criteria and objective evaluation criteria agreed; stakeholders identified and aligned; assumptions documented and validated; current vs ideal state articulated; underlying interests surfaced and common ground established; and the problem statement is specific, measurable, and solution-independent, with no embedded solution.

Produce a provisional, solution-independent restatement of the problem - explicitly marked to-be-validated, not yet agreed.

Return to understanding when new assumptions or implicit needs surface, context shifts, understanding feels incomplete, solutions are proposed prematurely, the problem statement embeds a solution, or stakeholders are misaligned.

Apply to following statement:

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. 2d ago First seen · 36 lines · 19 tokens per session scan A 2ee22473f642

Subscribe to this mod's changes

understand is a command published in the GitHub repository bjcoombs/ai-native-toolkit (30 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 435 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 2026-08-30.