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-analysis-of-competing-hypothesesgit 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-analysis-of-competing-hypotheses)<a href="https://agentmods.dev/skills/product-on-purpose/thinking-framework-skills/think-analysis-of-competing-hypotheses"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-analysis-of-competing-hypotheses/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-analysis-of-competing-hypotheses"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-analysis-of-competing-hypotheses.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 | $0.00129 | $0.01290 |
| Opus 5 | $0.00064 | $0.00645 |
| Sonnet 5 | $0.00026 | $0.00258 |
| Haiku 4.5 | $0.00013 | $0.00129 |
Grade A, and why
think-analysis-of-competing-hypotheses 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analysis of Competing Hypotheses (ACH)
ACH builds an evidence-by-hypothesis matrix, scores each item of evidence for how well it disconfirms each hypothesis, and favors the hypothesis with the least inconsistent evidence. It is a famous intelligence-analysis technique, and it was tested and found wanting: in randomized controlled studies it raised participants' confidence without improving accuracy, and showed no debiasing or judgment-quality gain. This skill therefore does not reproduce the matrix as if it were valid. It owns the request, leads with what the controlled evidence shows, and routes you to the evidence-based move your actual job needs. The output is an honest redirect brief, not a disconfirmation matrix with a declared winner.
Before you run this: what the controlled evidence shows
ACH is tier X (tested and found wanting, not merely undertested). On its own home population and stated purpose, the controlled record is null-to-negative:
- Otzipka (2025, Applied Cognitive Psychology): applying ACH significantly raised participants' confidence with no accuracy gain (confidence without accuracy).
- Dhami, Belton and Mandel (2019, Applied Cognitive Psychology): 50 intelligence analysts randomized; steps were skipped, bias effects were mixed, and ACH may have increased judgment inconsistency and error.
- Karvetski and Mandel (2020, Judgment and Decision Making, N=227): no gain in additivity, coherence, or consistency, and slightly reduced reliability.
- Whitesmith (2019); Maegherman et al. (2021); Dhami et al. (2024, the matrix layout specifically failed to reduce bias); Otzipka and Volbert (2026): no debiasing.
The mechanism's documented flaw: counting inconsistencies treats evidence items as independent and equally weighted, which they almost never are. Institutional adoption is not outcome evidence. So this skill will not hand you a filled matrix and a "least-inconsistent" verdict, because that artifact is exactly what the trials condemned. It states the caveat and redirects.
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 · 79 lines · 129 tokens per session scan A 06ffb8726b7d
think-analysis-of-competing-hypotheses 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 129 tokens to every session and 1,290 once invoked, about $0.0006 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".