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.
git clone --depth 1 https://github.com/tkellogg/open-strixnpx agentmods add skills/tkellogg/open-strix/prediction-reviewWrote 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/tkellogg/open-strix/prediction-review)<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>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.01953 |
| Opus 5 | $0.00023 | $0.00977 |
| Sonnet 5 | $0.00009 | $0.00391 |
| Haiku 4.5 | $0.00005 | $0.00195 |
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.
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:
- Identify what you got wrong
- Update a memory block or file with what you learned
- 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)
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.
- 8d ago First seen · 187 lines · 46 tokens per session scan A 143f8e9054bc
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…