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 ngocsangyem/MeowKit --skill decision-frameworkgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/decision-framework)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/decision-framework"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/decision-framework/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/ngocsangyem/meowkit/decision-framework"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/decision-framework.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 | $0.00040 | $0.00990 |
| Opus 5 | $0.00020 | $0.00495 |
| Sonnet 5 | $0.00008 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
mk:decision-framework 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 6d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Framework Builder
Structures expert judgment into repeatable, auditable decision systems for recurring high-stakes choices.
When to Use
Activate when:
- User asks "how should we handle X cases?" or "build triage system"
- Designing escalation protocols or case management workflows
- Billing ops, support, returns, incident response, compliance decisions
- Any domain with classified decision types and routing rules
Phase Anchor
Phase: 1 (Plan) — Produces a decision framework document. Handoff: Developer agent implements the decision logic in code.
Failure Handling
- Domain unclear: Ask user for 3 example cases. Derive taxonomy from examples.
- No domain expert available: Flag output as
needs-expert-input. Mark uncertain classifications explicitly.
Process (7 Steps)
Step 1: Identify Decision Type
Clarify the recurring decision being structured. What is decided? Who decides? How often?
Step 2: Build Classification Taxonomy
Load references/decision-tree-template.md. Map every case type into mutually exclusive categories. Aim for 3-7 top-level buckets — too few collapses distinct cases, too many creates lookup overhead.
Step 3: Define Sequential Decision Rules
Order rules by: Safety > Compliance > Economics > Speed. Never let speed override safety. Document the reasoning for each rule's position in the sequence.
Step 4: Create Weighted Scoring
Load references/weighted-scoring-guide.md. Define 3-5 factors with weights summing to 100%. Calibrate against 3 historical cases.
Step 5: Define Escalation Protocol
Load references/escalation-protocol-template.md. Map 4 escalation levels: Expert → Manager → Director → VP. Each level must have authority scope, timeline, and escalation trigger.
Step 6: Add Communication Templates
Load references/communication-patterns.md. Select tone per relationship state: Routine / Significant / Crisis. Customize placeholders.
Step 7: Document Edge Cases
Load references/edge-case-discovery.md. Collect edge cases from team ("what surprised you?"). Document each as: situation → why obvious approach fails → correct approach.
What ships with it
8 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.
- references/communication-patterns.md 3.8 KB
- references/decision-tree-template.md 2.4 KB
- references/edge-case-discovery.md 2.5 KB
- references/escalation-protocol-template.md 3.0 KB
- references/examples/example-billing-ops.md 4.0 KB
- references/examples/example-incident-response.md 4.8 KB
- references/examples/example-returns-triage.md 2.9 KB
- references/weighted-scoring-guide.md 3.5 KB
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.
- 6d ago First seen · 103 lines · 40 tokens per session scan A 5bdd00ad48e7
mk:decision-framework is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 990 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after /phx:plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
CSOC Operations & Playbook Automation
SOC alert triage, incident playbook automation, escalation workflows, shift reporting, and SOC KPI tracking.
plan
Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).
punch-list-manager
Digital punch list management for construction project closeout. Track deficiencies, assign corrections, photo documentation, and completion verification.