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/projectnpx skills add victoriacity/openakari --skill projectgit 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/project)<a href="https://agentmods.dev/skills/victoriacity/openakari/project"><img src="https://agentmods.dev/badge/skills/victoriacity/openakari/project.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 | $0.00032 | $0.02733 |
| Opus 5 | $0.00016 | $0.01367 |
| Sonnet 5 | $0.00006 | $0.00547 |
| Haiku 4.5 | $0.00003 | $0.00273 |
Grade A, and why
project 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/project [argument]
Unified skill for creating new research projects. Two modes:
-
/project propose [topic]— Agent-initiated. Scans the repo for research gaps, assesses whether a gap warrants a project, and writes a formal proposal for PI review. Proposals require approval to activate. If topic is omitted, scans for candidate gaps first. -
/project scaffold <description>— Human-initiated. Interactive interview to understand what the human wants, then scaffolds the project directory with all required files. No approval needed — the human requesting it has authority.
When to use which mode:
- You identified a research gap and want to propose an investigation →
propose - A human asked you to set up a new project →
scaffold
Mode: propose
Agent-initiated project proposal. All inputs are repo-resident (experiment findings, open questions, literature gaps, operational patterns).
Principles
-
Ground in evidence, not speculation. Every claim about a gap must cite a specific source: an experiment finding, an operational pattern, a literature gap, an open question.
-
Research questions over implementation requests. A proposal must center on a question that produces knowledge when answered. "Build a dashboard" is not a project — "Does real-time visualization reduce PI intervention rate?" is.
-
Proportionate scope. Prefer focused investigations over broad surveys. A project that answers one specific question well is more valuable than one that vaguely addresses five.
-
Explicit uncertainty. State what you don't know. If feasibility depends on an untested assumption, propose a pilot step.
Step 1: Identify candidate gaps
If a topic was provided, skip to Step 2. Otherwise, scan these sources:
- Open questions — Read
## Open questionssections in all active project READMEs. Look for questions not addressed by existing experiments. - Experiment recommendations — Scan completed
EXPERIMENT.mdfiles for unactioned recommendations (Recommendations, Proposed solutions, Next steps) beyond current project scope. - Cross-session patterns — Check
.scheduler/metrics/sessions.jsonlfor recurring operational issues. - Literature gaps — Check
literature/synthesis.mdfiles for gaps between existing literature and current questions. - Roadmap gaps — Read
docs/roadmap.mdandprojects/akari/plans/long-term-roadmap.mdfor capability gaps.
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 · 310 lines · 32 tokens per session scan A b4d07c77d851
project is a skill published in the GitHub repository victoriacity/openakari (47 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 2,733 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.
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…