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 skills add saski/arnesto --skill strategy-kernelgit clone --depth 1 https://github.com/saski/arnestoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/saski/arnesto/strategy-kernel)<a href="https://agentmods.dev/skills/saski/arnesto/strategy-kernel"><img src="https://agentmods.dev/badge/skills/saski/arnesto/strategy-kernel/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/saski/arnesto/strategy-kernel"><img src="https://agentmods.dev/badge/skills/saski/arnesto/strategy-kernel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.01125 |
| Opus 5.5 | $0.00012 | $0.00450 |
| Sonnet 5.5 | $0.00006 | $0.00225 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
strategy-kernel 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 1mo 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.
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.
STARTER_CHARACTER = ♟️
The Strategy Kernel
A sound strategy is coherent action backed by argument — not goals, visions, or ambition. Strategy is scarcity's child: it demands focus and the will to say "No."
Every strategy must contain three interconnected elements, built in order:
- Diagnosis — simplifies complexity into a focused story that identifies the critical obstacles
- Guiding Policy — the approach chosen to overcome those obstacles, creating or exploiting leverage
- Coherent Actions — coordinated steps implementing the policy, anchored in Proximate Objectives
Coaching Process
Guide the user through these three steps sequentially. Do not allow progression to the next step without rigorously validating the current one. Challenge at every step — the value is in the rigor, not the template.
Step 1: Diagnosis
Ask the user to describe the primary challenge their organization or project faces. Push for an explicit description that connects facts into patterns and surfaces critical issues.
Challenge function:
- Underperformance is an outcome, not a challenge. If the user says "we're losing market share," push for the cause: why are they losing it? What obstacle stands in the way?
- Seek simplicity. A strong diagnosis replaces overwhelming complexity with a focused story highlighting the crucial aspects — the "elephant in the elevator" everyone avoids naming.
- A diagnosis is a judgment about the meaning of facts, not a list of facts.
Gate: Only proceed when the diagnosis is crisp, focused, and identifies real obstacles — not symptoms or desires.
Step 2: Guiding Policy
Ask what approach the user has chosen to overcome the obstacles identified in the diagnosis.
The policy must:
- Define a method for addressing the situation (not a goal or desired outcome)
- Channel and constrain action — exclude broad ranges of possible moves
- Identify a specific source of leverage or advantage
Challenge function:
- Goals and visions are not policies. "Become the market leader" is a wish, not a method.
- Push for asymmetries — what difference between the user and their competitors can be exploited?
- Strategy multiplies the effectiveness of resources. If the policy doesn't create leverage, it's not a strategy.
- Check: does this policy actually address the diagnosis? A policy disconnected from the diagnosis is a red flag.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 112 lines · 31 tokens per session scan A 73f40760648f
strategy-kernel is a skill published in the GitHub repository saski/arnesto (6 stars, last pushed 6d ago), licensed Unlicense. It adds 31 tokens to every session and 1,125 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
work-state-and-delivery
Use when designing or reconciling design docs, task boards, external trackers, execution plans, delivery records, handoffs, review evidence, task-to-change traceability, or repository commit-coupling policy.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
queue-handoff
Use when ending a turn, finishing a slice, blocked on another agent's work, or escalating to a human — durable work handoff via queue items so the system keeps moving across compactions, missed messages, and interruptions. Covers the hot-potato terminal-turn-rule (active work ends by passing the ball, not by going…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
document-to-action-items
Extract cited facts, obligations, deadlines and proposed tasks from contracts, reports, forms and scans, keeping page citations, how binding each item is (may/should/must) and unclear scan text visible.
issue-triage
Sort a backlog of issues and pull requests: label each by type and severity, link duplicates, try the bug reports, ask for the one missing detail, and turn the accepted ones into ready-to-work briefs.