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 allemaar/open-skills --skill insight-anglesgit clone --depth 1 https://github.com/allemaar/open-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/allemaar/open-skills/insight-angles)<a href="https://agentmods.dev/skills/allemaar/open-skills/insight-angles"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/insight-angles/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/allemaar/open-skills/insight-angles"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/insight-angles.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 | $0.00187 | $0.03128 |
| Opus 5 | $0.00093 | $0.01564 |
| Sonnet 5 | $0.00037 | $0.00626 |
| Haiku 4.5 | $0.00019 | $0.00313 |
Grade A, and why
insight-angles 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 10d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/insight-angles
A lens-based, multi-pass discovery engine. Where /insight-explore asks "what are the ways to build this?" and /insight-adversarial attacks for flaws via personas, insight-angles asks "what frames, connections, assumptions, and second-order effects are not yet visible?" — and finds them by pointing the right lenses at the subject. It can run each lens as a cold sub-agent (fresh context, no anchoring) — independence is what makes discovery work, the same reason /cold-review outperforms inline /verify at finding things — and picks cold vs inline per subject, asking only when it isn't sure. Read-only and advisory — it surfaces, never decides or changes anything.
Structured execution spec:
protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the@STAMPdate.
The lens roster (seed, not ceiling)
17 families, grouped by what they perturb. Core = candidate for most subjects; Specialist = domain-triggered. Always also derive dynamic, subject-specific lenses (see below) — the roster is a seed.
| Family | Tier | Operators | Best for |
|---|---|---|---|
| Reframe | Core | inversion · via-negativa ("what guarantees failure?") · pre/pro-mortem · meta-frame ("right question?") · first-principles · counterfactual | stuck / ambiguous / strategic |
| Analogy | Core | cross-domain · structural isomorphism · biological/evolutionary · historical parallel | novel problems, naming, design |
| Temporal | Core | precedent · path-dependency · future-back · cyclicality · "why now?" · lifecycle stage | timing, strategy, forecasts |
| Perspective | Core | absent stakeholder · adversary/competitor · payer vs beneficiary · future maintainer/user · novice vs expert | product, org, strategy |
| Systems | Core | feedback loops · incentives · externalities · 2nd/3rd-order · stocks/flows · bottlenecks | policy, platform, ecosystem |
| Constraint | Core | relax · tighten 10× · swap · the binding constraint · fixed vs assumed-fixed | design, optimization, planning |
| Epistemic | Core | load-bearing assumption · weakest evidence · what-would-change-our-mind · unknown-unknowns · information asymmetry · observability | research, forecasts, high-stakes |
| Zoom | Specialist | in · out · across · boundary/interface | architecture, scope, scale |
| Formal/Structural | Specialist | invariants · symmetries · limits & edge cases · conservation · the formal model | technical, math |
| Cartography/Representation | Specialist | viewpoint/view/model separation · level-of-detail · epistemic legend · one-fact-one-home · cross-map anchors · ratification status | architecture, portfolios, complex operating systems |
| Power & Politics | Specialist | who holds/gains/loses power · gatekeepers · coalitions · feasible vs optimal | org, strategy, governance |
| Human/Behavioral | Specialist | cognitive biases · status/identity/fear/desire · friction & defaults · rewarded behavior | product, UX, change mgmt |
| Economic/Value | Specialist | cost structure · value capture · opportunity cost · marginal vs fixed · who pays | product, business |
| Aesthetic/Elegance | Core | simplicity · conceptual integrity · symmetry · the elegant version · what to remove | design, UX, DX, ergonomics, writing, code |
| Values/Ethical | Specialist | harm-bearer · value tradeoffs · whose values are encoded · rights vs utility · intergenerational | values-laden / policy decisions |
| Narrative | Specialist | story told · hero/villain · the spin · meta-narrative · positioning | comms, positioning, naming |
| Activation/Engagement | Specialist | first-win · time-to-first-value (TTFV) · the hook / aha-moment · activation arc · drop-off & friction-to-activation · juice (satisfying feedback) | onboarding, first-run, tutorials, adoption funnels, growth/UX |
What ships with it
1 file 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.
- 10d ago First seen · 140 lines · 187 tokens per session scan A 191bbba20f47
insight-angles is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed 23d ago), licensed Apache-2.0. It adds 187 tokens to every session and 3,128 once invoked, about $0.0009 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
polis-protocol
Set up and run a self-improving, multi-vendor AI agent team with the Polis Protocol — a markdown polis/ folder where each agent is a citizen with a capability card, tasks are contracts routed to whoever has the best track record by a learning router, settled work files lessons that compound into team memory, and…
media
Skill "media" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
_data
Skill "_data" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.