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 martineserios/thebrana --skill decision-matrixgit clone --depth 1 https://github.com/martineserios/thebranaWrote 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/martineserios/thebrana/decision-matrix)<a href="https://agentmods.dev/skills/martineserios/thebrana/decision-matrix"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/decision-matrix/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/martineserios/thebrana/decision-matrix"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/decision-matrix.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 | $0.00098 | $0.01931 |
| Opus 5.5 | $0.00039 | $0.00772 |
| Sonnet 5.5 | $0.00020 | $0.00386 |
| Haiku 4.5 | $0.00010 | $0.00193 |
Grade A, and why
decision-matrix 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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- decision-matrix — 100% identical, 7 lines differ
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Matrix
Overview
A decision matrix scores each option on each criterion, making subjective factors visible and comparable. It includes weighted criteria, sensitivity analysis, and clear recommendations.
Quick example:
| Option | Cost (30%) | Speed (25%) | Quality (45%) | Weighted Score |
|---|---|---|---|---|
| Option A | 8 (2.4) | 6 (1.5) | 9 (4.05) | 7.95 ← Winner |
| Option B | 6 (1.8) | 9 (2.25) | 7 (3.15) | 7.20 |
| Option C | 9 (2.7) | 4 (1.0) | 6 (2.7) | 6.40 |
Option A wins despite not being fastest or cheapest because quality matters most (45% weight).
Workflow
Copy this checklist and track your progress:
Decision Matrix Progress:
- [ ] Step 1: Frame the decision and list alternatives
- [ ] Step 2: Identify and weight criteria
- [ ] Step 3: Score each alternative on each criterion
- [ ] Step 4: Calculate weighted scores and analyze results
- [ ] Step 5: Validate quality and deliver recommendation
Step 1: Frame the decision and list alternatives
Ask user for decision context (what are we choosing and why), list of alternatives (specific named options, not generic categories), constraints or dealbreakers (must-have requirements), and stakeholders (who needs to agree). Understanding must-haves helps filter options before scoring. See Framing Questions for clarification prompts.
Step 2: Identify and weight criteria
Collaborate with user to identify criteria (what factors matter for this decision), determine weights (which criteria matter most, as percentages summing to 100%), and validate coverage (do criteria capture all important trade-offs). If user is unsure about weighting → Use resources/template.md for weighting techniques. See Criterion Types for common patterns.
Step 3: Score each alternative on each criterion
For each option, score on each criterion using consistent scale (typically 1-10 where 10 = best). Ask user for scores or research objective data (cost, speed metrics) where available. Document assumptions and data sources. For complex scoring → See resources/methodology.md for calibration techniques.
What ships with it
3 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.
- 2mo ago First seen · 183 lines · 98 tokens per session scan A 4d2443b2fe6c
decision-matrix is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 1,931 once invoked, about $0.0004 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 2026-08-31.
decision-matrix compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| decision-matrixmartineserios/thebrana | Skill | 3 | 2d ago | MIT | A | 98 | Claude Code, Codex |
| prumputun/cc-thingz | Skill | 497 | 13d ago | MIT | A | 51 | Claude Code |
| root-cause-investigatorumputun/cc-thingz | Skill | 497 | 13d ago | MIT | A | 53 | Claude Code |
| crap-analyzerswingerman/engineer | Skill | 164 | 5d ago | MIT | A | 109 | Claude Code |
| initarchcore-ai/plugin | Skill | 58 | 1mo ago | Apache-2.0 | A | 235 | Claude Code |
| eu-ai-act-checkpitimon/8-habit-ai-dev | Skill | 3 | 5d ago | MIT | A | 24 | Claude Code |
| workflowpitimon/8-habit-ai-dev | Skill | 3 | 5d ago | MIT | A | 36 | Claude Code |