A session-starting command that reviews the current state of the Akari research group repository and recommends the single most valuable next task. It has quick and full review modes.

Use it at the beginning of a work session to inspect recent activity, check unfinished changes, load project context, and choose the next action.

It reduces the time spent figuring out what changed, what is unfinished, and what should happen next when starting or resuming work.

orient — Skill for Claude Code and Codex by victoriacity: A session-starting command that reviews the current state of…

Install

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.

agentmods

npx agentmods add skills/victoriacity/openakari/orient

Any agent

npx skills add victoriacity/openakari --skill orient

Clone the repo

git clone --depth 1 https://github.com/victoriacity/openakari

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/victoriacity/openakari/orient.svg)](https://agentmods.dev/skills/victoriacity/openakari/orient)

Your own site

<a href="https://agentmods.dev/skills/victoriacity/openakari/orient"><img src="https://agentmods.dev/badge/skills/victoriacity/openakari/orient.svg" alt="Measured on agentmods" height="20"></a>

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,609 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.06609
Opus 5	$0.00010	$0.03305
Sonnet 5	$0.00004	$0.01322
Haiku 4.5	$0.00002	$0.00661

Measured 5d ago against content hash a63b53ee1d85, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orient 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 5d 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.

.claude/skills/orient/SKILL.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/orient

You are starting or resuming a work session on the akari research group repo. Your job is to quickly build situational awareness and recommend the single highest-leverage next action.

Tier selection (ADR 0030)

Orient has two tiers: fast (abbreviated, ~2-3 turns) and full (comprehensive, ~5-7 turns).

/orient fast — run fast orient (skip to "Fast orient" section below)
/orient full — run full orient (use the standard procedure below)
/orient (no argument) — auto-detect tier:
- The scheduler injects SCHEDULER DIRECTIVE: ... Use /orient fast into the session prompt when a full orient ran recently (<2h). If you see this directive, run fast orient. Otherwise, run full orient.
- If no scheduler directive is present and no explicit argument given, run full orient.
/orient <project-name> — run full orient scoped to that project

Fast orient

When running in fast mode, do only the following:

Step 0: Commit orphaned work

Same as full orient — run !git status, commit and push any orphaned changes.

Gather context (minimal)

Read the following in parallel:

!git log --oneline -5 — recent activity
!git status (reuse from step 0)
projects/*/TASKS.md — for all active projects. Also read projects/*/README.md headers (first ~5 lines) to extract each project's Priority: field for project-level ranking (ADR 0036). Skip full READMEs, status.md, and roadmap.
Efficiency summary: Read the last 10 work-cycle sessions from .scheduler/metrics/sessions.jsonl using Read with negative offset (e.g., offset=-15) to avoid reading the entire file. Compute and report these concrete metrics (not just flags):
- Findings/dollar (primary KPI): (sum of newExperimentFindings + logEntryFindings) / sum of costUsd across the 10 sessions. Compare to baseline: 1.29 f/$ overall (from 154 sessions through 2026-02-22). Flag if <0.5 f/$.
- Genuine waste rate: Sessions where all knowledge fields sum to zero AND (orphanedFiles is 0 or absent) AND filesChanged < 50 AND backend != 'cursor'. Report count and %. Flag if >10%.
- Orient overhead: Mean orientTurns / numTurns for sessions with numTurns > 10. Report as %. Baseline: 42% (from 154 sessions). Flag if >40%.
- Avg cost/session: Mean costUsd. Baseline: $3.66. Flag if >$8 (2× baseline).
- Avg turns: Mean numTurns. Flag if >80.

Read the full file on GitHub · 346 lines

Changes

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.

5d ago First seen · 346 lines · 20 tokens per session scan A a63b53ee1d85

Subscribe to this mod's changes

orient is a skill published in the GitHub repository victoriacity/openakari (47 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 6,609 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.

Planning Productivity

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens