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-iceberg-modelgit 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-iceberg-model)<a href="https://agentmods.dev/skills/product-on-purpose/thinking-framework-skills/think-iceberg-model"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-iceberg-model/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-iceberg-model"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-iceberg-model.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 | $0.00101 | $0.01268 |
| Opus 5 | $0.00051 | $0.00634 |
| Sonnet 5 | $0.00020 | $0.00254 |
| Haiku 4.5 | $0.00010 | $0.00127 |
Grade A, and why
think-iceberg-model 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iceberg Model
The default response to a problem is to react to the visible event. The iceberg model resists that by moving the problem down four levels, from the tip toward the mass under the water: the event (what just happened), the pattern (what has been happening over time), the structures (the policies, incentives, resource flows, and feedback loops that generate the pattern), and the mental models (the beliefs and assumptions that hold those structures in place). Descending past the event is the work, because structure and mindset are where higher-leverage interventions sit. Each level is paired with the intervention it implies: event-level fixes are reactive and low-leverage, structure- and model-level fixes are higher-leverage and slower. The output is an iceberg, not a discussion.
When to Use
- A problem keeps recurring despite repeated event-level fixes, hinting at a structural cause.
- A symptom is being treated as a one-off when it is the latest instance of a pattern.
- The real question is "why does this keep happening, and where do we actually intervene?"
- There is appetite to consider structural or mindset interventions, not only quick reactive fixes.
When NOT to Use
- A simple, linear, single-cause problem. One event, one obvious cause, a known fix. Forcing four levels manufactures false depth; say it is a simple cause and stop.
- Mapping forward consequences ("if we do this, then what happens next?"). That is the futures wheel, which maps outward to effects. The iceberg maps downward to causes.
- Auditing one person's reasoning from data to conclusion. That is the ladder of inference check. The iceberg is about systemic levels of causation, not one person's inference chain.
- As a ritual that fills four labeled boxes with no honest descent and no intervention paired to each level. A tidy diagram with no leverage is theater.
What ships with it
6 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 · 65 lines · 101 tokens per session scan A 686f794c659a
think-iceberg-model 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 101 tokens to every session and 1,268 once invoked, about $0.0005 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.
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…
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).
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".