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 agentmods add skills/abilityai/cornelius/detect-tensionsnpx skills add Abilityai/cornelius --skill detect-tensionsgit 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/detect-tensions)<a href="https://agentmods.dev/skills/abilityai/cornelius/detect-tensions"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/detect-tensions.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00967 |
| Opus 5 | $0.00010 | $0.00483 |
| Sonnet 5 | $0.00004 | $0.00193 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
detect-tensions 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 4d 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.
Detect Productive Tensions
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change - the top entry of
metadata.changelogabove - e.g.detect-tensions vX.Y - recent: <summary>. Then proceed.
Scans the knowledge base for productive contradictions: note pairs with high semantic similarity but opposing conclusions. These tension zones are where the most valuable articles and frameworks emerge.
State Dependencies
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| Enrichments | resources/brain-graph/data/graph_enrichments.json |
✓ | ✓ | Tension records saved |
| FAISS Index | resources/local-brain-search/data/brain.faiss |
✓ | Similarity search | |
| Metadata | resources/local-brain-search/data/brain_metadata.pkl |
✓ | Note content |
Process
Step 1: Run tension detection
Default thresholds (similarity > 0.75, divergence > 0.3):
cd $PROJECT_ROOT/resources/brain-graph
../local-brain-search/venv/bin/python cli.py tensions
Broader search (more results, lower quality):
../local-brain-search/venv/bin/python cli.py tensions --similarity 0.70 --divergence 0.2
Step 2: Filter false positives, then present synthesis opportunities
The raw count is dominated by false positives - discard them before presenting:
- Boilerplate / near-duplicate pairs. The signature is high similarity with maximal divergence (e.g. sim ≈ 1.00, divergence ≈ 1.00), and pairs where both notes are changelogs, registries, or near-identical restatements of one principle. These are detector artifacts, not contradictions.
Keep only pairs that assert genuinely opposing conclusions about the same question. For each surviving tension, explain:
- What the two notes assert
- Why they contradict
- What synthesis opportunity exists (article topic, framework potential)
Step 3: Track existing tensions
../local-brain-search/venv/bin/python cli.py status --json
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.
- 4d ago First seen · 79 lines · 20 tokens per session scan A dcab8c2ed61a
detect-tensions is a skill published in the GitHub repository Abilityai/cornelius (105 stars, last pushed 11d ago), licensed MIT. It adds 20 tokens to every session and 967 once invoked, about $0.0001 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…