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 uchicago-dsi/ai-sci-skills --skill sensemakinggit clone --depth 1 https://github.com/uchicago-dsi/ai-sci-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/uchicago-dsi/ai-sci-skills/sensemaking)<a href="https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/sensemaking"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/sensemaking/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/uchicago-dsi/ai-sci-skills/sensemaking"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/sensemaking.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 | $0.00059 | $0.00804 |
| Opus 5 | $0.00030 | $0.00402 |
| Sonnet 5 | $0.00012 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
sensemaking 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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sensemaking
Use It As A Default Habit
- Compose this skill with domain skills instead of replacing them.
- Use it whenever you are about to trust, summarize, or act on a finding.
- Default question: does this result actually make sense, and if so, what should change because of it?
Use This Output Contract
When using this skill, structure the reasoning as:
- Observation: what happened.
- Expected: what you thought would happen instead.
- Nearest reference: the baseline, sibling case, prior run, known-good path, or control.
- Best explanation: the most plausible mechanism right now.
- Falsifier: one observation that would seriously weaken that explanation.
- Decision impact: what changes, or why nothing changes.
- Baseline disposition: whether the nearest valid baseline remains active or has been superseded, and by what evidence.
- Falsification scope: the exact hypothesis or changed delta rejected, plus the parent method or unchanged components that remain live.
Apply These Rules
- Separate observation from interpretation.
- Compare against the nearest useful reference, not an abstract ideal.
- Say why the chosen reference is the right baseline or control; if no fair baseline exists, weaken the conclusion.
- Prefer mechanistic explanations over labels such as "noisy", "unstable", or "weird".
- When the mechanism is spatial, temporal, structural, or artifact-like, inspect or create the nearest useful visual comparison instead of relying on scalar metrics alone.
- Ask whether the finding is strong enough to change the next action.
- If the result does not change the decision, say so explicitly.
- If the result contradicts the current story, update the story.
Preserve The Best Baseline
- Keep the best valid baseline active until a prospectively defined successor beats it on the same decision readouts.
- Attribute a failure only to what changed relative to that baseline. Failure of an additive rescue rejects the rescue or combination, not the retained baseline.
- Before pivoting, name the baseline, changed delta, result, exact hypothesis falsified, hypotheses not falsified, and retained active path.
- Scope stop rules narrowly. Do not retire a successful parent method because a broader extension or challenger failed unless that parent was directly retested and failed.
What ships with it
2 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.
- 10d ago First seen · 78 lines · 59 tokens per session scan A 367837942ebb
sensemaking is a skill published in the GitHub repository uchicago-dsi/ai-sci-skills (17 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 804 once invoked, about $0.0003 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 2026-08-31.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…