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/victoriacity/openakari/gravitynpx skills add victoriacity/openakari --skill gravitygit clone --depth 1 https://github.com/victoriacity/openakariWrote 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/victoriacity/openakari/gravity)<a href="https://agentmods.dev/skills/victoriacity/openakari/gravity"><img src="https://agentmods.dev/badge/skills/victoriacity/openakari/gravity.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 | $0.01245 |
| Opus 5 | $0.00010 | $0.00622 |
| Sonnet 5 | $0.00004 | $0.00249 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
gravity 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gravity <pattern description or "scan">
You are evaluating whether recurring patterns should move downward in the capability stack — from manual practice into tools, workflows, or model behavior. The /orient skill detects gravity signals; this skill evaluates them.
The argument is either a specific pattern to evaluate (e.g., "agents keep manually computing metric breakdowns") or "scan" to search for gravity candidates across the repo.
If argument is "scan"
Search for gravity signals across the repo:
- Read
docs/status.mdand all active project READMEs (Log sections) andTASKS.mdfiles. - Grep for recurring patterns:
- Similar commands or procedures appearing in multiple log entries
- Manual steps described repeatedly
- Workarounds or hacks mentioned in logs or open questions
- TODOs that keep reappearing across sessions
- Check
.claude/skills/— are any skills encoding judgment that has matured enough to become convention (L2) or schema (L1)? - Check
infra/— are there patterns in project code that should be extracted into shared tooling?
Produce a candidate list, then evaluate each candidate below.
For each gravity candidate
Step 1: Establish recurrence
- How many times has this pattern appeared? Cite specific log entries, files, or sessions.
- How consistent is it? Same pattern each time, or variations?
- Is it still evolving? A pattern that changes each time it appears is not yet stable enough to formalize.
A pattern must appear at least 3 times in substantially similar form before formalization is justified. If it has appeared fewer than 3 times, note it as "watch" rather than "act."
Step 2: Identify current layer and target layer
Where does the pattern currently live?
| Current state | Gravity layer |
|---|---|
| Human does it manually each session | Manual |
| Written as a convention/rule in CLAUDE.md | Convention |
| Encoded as a skill prompt | Skill |
| Implemented as a script in infra/ | Code |
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 · 129 lines · 20 tokens per session scan A 420d62e172cb
gravity is a skill published in the GitHub repository victoriacity/openakari (47 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 1,245 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…