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 product-on-purpose/thinking-framework-skills --skill think-ethical-matrixgit clone --depth 1 https://github.com/product-on-purpose/thinking-framework-skillsWrote 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/product-on-purpose/thinking-framework-skills/think-ethical-matrix)<a href="https://agentmods.dev/skills/product-on-purpose/thinking-framework-skills/think-ethical-matrix"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-ethical-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/product-on-purpose/thinking-framework-skills/think-ethical-matrix"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-ethical-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 | $0.00134 | $0.02097 |
| Opus 5 | $0.00067 | $0.01048 |
| Sonnet 5 | $0.00027 | $0.00419 |
| Haiku 4.5 | $0.00013 | $0.00210 |
Grade A, and why
think-ethical-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 12d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ethical Matrix
An "is this ethical?" debate over a concrete proposal tends to slide: it starts on one affected group, drifts to a principle, jumps to a different group, and never holds both axes at once - so the trade-offs that actually matter (a benefit to one party paid for by a burden on another, on a different principle) stay invisible. The ethical matrix refuses that slide. It cross-references the affected parties (rows) against a small fixed set of prima facie ethical principles (columns), and forces a concrete impact specification in every party-by-principle cell. The rows deliberately include parties who cannot speak for themselves - animals, ecosystems, future generations, absent groups - because they get a row whether or not anyone in the room represents them. The durable move is principled cross-referencing: making the trade-offs a single-axis analysis hides become visible and individually contestable.
Two design choices are load-bearing and frequently misunderstood. First, the matrix maps the moral terrain; it does not weigh it. The grid is not an algorithm and emits no verdict - the weighing happens in deliberation over the filled grid. Second, the cells are impact specifications ("how does this affect the wellbeing of small producers"), not perspective voicings ("what would small producers say"). That second point is what separates it from stakeholder perspective-taking. The output is an ethical matrix: a party-by-principle impact grid with each cell tagged factual or contested, a trade-off pattern read-out, and an explicit no-verdict footer.
When to Use
- A concrete proposal, technology, policy, or feature has multiple affected parties and a genuine moral trade-off among them: who gains, who pays, and on what dimension.
- Some affected parties have no voice - non-human, future, or absent groups that need representing even though nobody in the room speaks for them.
- An ethics debate keeps sliding between groups and principles without anyone noticing the slide, and disagreement needs to attach to specific cells rather than to vague unease.
- A group needs a shared, inspectable structure for a values trade-off, so a position can be defended cell by cell.
What ships with it
5 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.
- 12d ago First seen · 71 lines · 134 tokens per session scan A bc4d26934539
think-ethical-matrix is a skill published in the GitHub repository product-on-purpose/thinking-framework-skills (15 stars, last pushed today), licensed Apache-2.0. It adds 134 tokens to every session and 2,097 once invoked, about $0.0007 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 skills, from other repositories
ops-demo
CocoOps demo mode activator — populates .cocoplus/ops/demo/ with realistic mock data and sets cocoplus.toml [demo] enabled = true. Invoked via $ops demo.
acl-rule-analysis
Vendor-agnostic ACL and firewall rule analysis with shadowed rule detection, overly permissive rule identification, unused rule discovery, redundant rule flagging, and rule ordering optimization. Covers ACLs (Cisco/JunOS/EOS) and firewall policies (PAN-OS/FortiGate/CheckPoint).
add-analytics
Add Google Analytics 4 tracking to any project. Detects framework, adds tracking code, sets up events, and configures privacy settings.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
agent-team-orchestration
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4)…
agent-bom-enforce
Enforce security policies on MCP tool calls and block dangerous operations at runtime. Use when: "block risky calls", "apply policy", "proxy", "runtime protection", "policy enforcement", "intercept MCP calls".