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/bjcoombs/ai-native-toolkit/understandgit clone --depth 1 https://github.com/bjcoombs/ai-native-toolkitWhat 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 | $0.00019 | $0.00435 |
| Opus 5 | $0.00010 | $0.00217 |
| Sonnet 5 | $0.00004 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00044 |
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.
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:
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 · 36 lines · 19 tokens per session scan A 2ee22473f642
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.
Other commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
loop
Iteratively fix issues until all resolved or max iterations reached.
OpenSpec: Apply
Implement an approved OpenSpec change and keep tasks in sync.
auto-goal
goal 래퍼 — /goal 생성, 상태 확인, 완료/blocked handoff를 goal tool 또는 slash command로 연결합니다.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
implement-task
根据技术方案实施任务并输出实现报告.