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-abstraction-ladderinggit 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-abstraction-laddering)<a href="https://agentmods.dev/skills/product-on-purpose/thinking-framework-skills/think-abstraction-laddering"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-abstraction-laddering/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-abstraction-laddering"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-abstraction-laddering.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 | $0.00100 | $0.01446 |
| Opus 5 | $0.00050 | $0.00723 |
| Sonnet 5 | $0.00020 | $0.00289 |
| Haiku 4.5 | $0.00010 | $0.00145 |
Grade A, and why
think-abstraction-laddering 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.
Abstraction Laddering
Every problem arrives at some altitude, and the altitude is usually accidental: it is wherever someone happened to be standing when they noticed it. Too low and you optimize a detail that does not matter ("make the button blue"); too high and you produce a true but useless aspiration ("delight the customer"). Abstraction laddering moves the problem along one vertical axis - up by asking "why? / to what end?" and down by asking "how? / what specifically?" - to find the altitude at which it is actually workable. The output is an abstraction ladder, an ordered set of rungs with one chosen as the working level, not a discussion.
When to Use
- A request names a bare solution ("add a dashboard", "build an integration") but the purpose it serves is unstated.
- A problem is stated as a vague aspiration ("improve engagement", "be more strategic") with no concrete handle to act on.
- People are arguing past each other and may simply be working at different levels of the same problem.
- Before committing effort, to decide deliberately at what altitude to attack a problem rather than inheriting the accidental one.
When NOT to Use
- Altitude is not the issue. If the problem needs a different kind of reframing - a stakeholder shift, an inversion, an is/is-not boundary, or weighing several rival framings - use
think-problem-restatement, which generates those moves and converges on a chosen frame. This skill only moves up and down one axis. - The right level is already clear and agreed. Building a ladder for a well-located problem manufactures motion and wastes effort.
- To generate or choose solutions. Going down lists more concrete sub-problems to consider, not a chosen solution. Use an ideation skill (Question Burst, SCAMPER) to generate and a decision skill (Decision Option Review) to choose.
- To decompose a problem into all its parts. A ladder is a single vertical chain, not a branching breakdown. For that, use an issue tree.
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 · 65 lines · 100 tokens per session scan A 08ab50d78818
think-abstraction-laddering is a skill published in the GitHub repository product-on-purpose/thinking-framework-skills (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 100 tokens to every session and 1,446 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".