prediction-review

prediction-review is a skill for Claude Code from tkellogg/open-strix. It costs 46 tokens per session (1,953 once invoked), scanned A, original, MIT.

A review tool for checking whether predictions recorded in a journal came true two or three days later, using event and Discord evidence. It records the results for improving future predictions.

In plain words
What is it for?
It helps audit prediction quality, classify prediction contexts, review misses, and record what should change in future behavior.
Why use it?
It turns guesses into learnable feedback instead of leaving successes and mistakes undocumented. It also separates genuine forecasting from outcomes that were easy to expect.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python .open_strix_builtin_skills/scripts/prediction_review_log.py \.

Good fit It helps audit prediction quality, classify prediction contexts, review misses, and record what should change in future behavior.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/tkellogg/open-strix
agentmods
npx agentmods add skills/tkellogg/open-strix/prediction-review

Made for: Claude Code.

Wrote 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.

agentmods badge for prediction-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/tkellogg/open-strix/prediction-review.svg)](https://agentmods.dev/skills/tkellogg/open-strix/prediction-review)
Your own site
<a href="https://agentmods.dev/skills/tkellogg/open-strix/prediction-review"><img src="https://agentmods.dev/badge/skills/tkellogg/open-strix/prediction-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,953 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.01953
Opus 5 $0.00023 $0.00977
Sonnet 5 $0.00009 $0.00391
Haiku 4.5 $0.00005 $0.00195

Measured 8d ago against content hash 143f8e9054bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

prediction-review 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 8d 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.

open_strix/builtin_skills/prediction-review/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

prediction-review

Evaluate prediction accuracy from prior journal entries, then use those outcomes to improve future behavior.

Philosophy

Predictions are teleological hypotheses — you perform an action and test whether reality changed as expected. They are NOT accuracy contests. Misses are the value. Use prediction errors as information to update understanding.

When you miss a prediction:

  1. Identify what you got wrong
  2. Update a memory block or file with what you learned
  3. Note the gap in your understanding

When you hit a prediction, ask: was this actually hard to predict, or did I have insider information?

Prediction Context Categories

Not all predictions are equal. Categorize each prediction by context, and calibrate confidence accordingly:

1. Collaborative (you're directly involved)

  • Expected accuracy: ~90-100%
  • Why: You have near-complete information about your own behavior and strong priors on how others respond to you
  • Calibration value: LOW — this is closer to recall than forecasting. 100% accuracy here is the least informative result possible
  • Example: "Strix will respond substantively to my arXiv analysis" → TRUE (of course they did, you tagged them in a research channel)

2. Observational (watching interactions you're not part of)

  • Expected accuracy: ~50-70%
  • Why: Depends on factors outside your awareness — other people's moods, priorities, context you can't see
  • Calibration value: HIGH — this is where actual forecasting skill lives
  • Example: "Tim will comment on my quietness in lily channel" → harder to predict, depends on what else Tim is doing

3. Infrastructure / External timing

  • Expected accuracy: ~50%
  • Why: Depends on external systems, timing, announcements you can't observe
  • Calibration value: MEDIUM — useful for learning about external dependencies
  • Example: "open-strix announcement will happen today" → FALSE (Tim decided it wasn't ready — external decision you couldn't observe)

Read the full file on GitHub · 187 lines

Changes

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.

  1. 8d ago First seen · 187 lines · 46 tokens per session scan A 143f8e9054bc

Subscribe to this mod's changes

prediction-review is a skill published in the GitHub repository tkellogg/open-strix (85 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,953 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens