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 Abilityai/cornelius --skill reasoning-checksgit clone --depth 1 https://github.com/Abilityai/corneliusWrote 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/abilityai/cornelius/reasoning-checks)<a href="https://agentmods.dev/skills/abilityai/cornelius/reasoning-checks"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/reasoning-checks/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/abilityai/cornelius/reasoning-checks"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/reasoning-checks.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 | $0.00085 | $0.02092 |
| Opus 5.5 | $0.00034 | $0.00837 |
| Sonnet 5.5 | $0.00017 | $0.00418 |
| Haiku 4.5 | $0.00009 | $0.00209 |
Grade A, and why
reasoning-checks 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reasoning Checks
ℹ️ First, set expectations: print one line with this skill's version and its most recent change - the top of
metadata.changelog- e.g.reasoning-checks v1.0 — recent: initial four-check contract. Then proceed. (Skip the banner when applied silently inside a consuming skill.)
Purpose
The calibration counterpart to the Thinking Geometries. The 2026-07-31 self-audit found the reasoning repertoire strong on discovery and synthesis but thin on calibration - everything runs from the inside view, and a graph this connected (50k+ edges, spreading activation) is structurally prone to falling in love with its own semantic connections. These checks close the gap at the two moments that matter: before advice is given and before a conclusion crosses the endorsement boundary.
Contract rule (the SOURCE-AUTHORITY.md pattern): this file is the single source of truth for the check definitions. Consuming skills reference it and apply the checks; they never copy the definitions inline. Change a check here, not in consumers.
State Dependencies
| Source | Location | Read | Write |
|---|---|---|---|
| Core fingerprint (live) | resources/local-brain-search/run_connections.sh --hubs --json and --bridges --json |
✓ | |
| Core fingerprint (fallback) | knowledge-base-analysis.md → "Core hubs" / "Core bridges" tables (note the analysis date) |
✓ | |
| Cited notes' frontmatter | Brain/**/*.md (provenance: field) |
✓ |
Never writes. Output blocks are embedded in the consuming skill's own artifact or answer. All reads are lookups, not retrievals - nothing here trains q-values.
The Four Checks
Check 1 - Epistemic Inversion (pre-mortem)
When: always, before any recommendation or conclusion is finalized.
Assume the conclusion is wrong and work backwards. Required output block:
### Epistemic Inversion
- **Failure assumption:** it is 12 months out and this [recommendation | conclusion] proved wrong.
- **Causal autopsy:** most likely reason it failed: [specific mechanism]
- **Specific falsifier:** we will know it failed if [observable event / metric crossing a threshold / dated milestone]
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 · 131 lines · 85 tokens per session scan A 18c7d35e2d98
reasoning-checks is a skill published in the GitHub repository Abilityai/cornelius (110 stars, last pushed 8d ago), licensed MIT. It adds 85 tokens to every session and 2,092 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-09.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…