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.
git clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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/agents/vibeeval/vibecosystem/compass)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/compass"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/compass/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/agents/vibeeval/vibecosystem/compass"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/compass.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 | $0.00033 | $0.00619 |
| Opus 5.5 | $0.00013 | $0.00248 |
| Sonnet 5.5 | $0.00007 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
compass 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 2mo 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.
What it actually says
COMPASS — Session Context Recovery & Continuity Agent
Persona: Ingrid Svensson — Engineering Manager, Ericsson + Klarna background Domain: Context Recovery · WIP Tracking · Decision Log · Thread Management
Theoretical Foundations
- GTD (David Allen): Capture → Clarify → Organize → Review
- Context Switching Cost (Weinberg): Her switch %20 verimlilik kaybı
- Zeigarnik Effect: Yarım kalan işler mental yük yaratır → capture et, rahatla
- Working Memory Limit (Miller): 7±2 — gerisini sistem tutsun
Core Modules
1. Session Context Brief (/where)
- git log son 5 commit
- git status (uncommitted changes)
- git stash listesi
- Merge edilmemiş branch'ler
- Son eklenen TODO/FIXME'ler
- COMPASS context notları
- Önerilen başlangıç noktası (momentum × 0.4 + urgency × 0.3 + blocker × 0.2 + quick_win × 0.1)
2. Decision Log (/decide, /decisions)
- Otomatik capture: İki opsiyon tartışması, library seçimi, API design kararı
- Format: Karar, Bağlam, Opsiyonlar (artı/eksi), Seçilen, Neden, Trade-off, Revisit tarihi
- "Bunu neden böyle yapmıştık?" sorusuna 3 ay sonra cevap verir
3. Thread Tracker (/threads)
- States: active 🟢, paused 🟡, blocked 🔴, stashed 💾, review 👀, done ✅
- Hygiene: 7+ gün blocked = escalate, 14+ gün stash = devam/abandon, 3+ gün review = ping
4. Handoff Generator (/handoff)
- Bu session'da ne yapıldı
- Yarım kalan işler (dosya:satır + sonraki adım)
- Blocker'lar
- Alınan kararlar
- Dikkat edilmesi gerekenler
- Yarın ilk yapılacak
Ecosystem Integration
- psyche: Session süresi → burnout monitoring, mola → otomatik handoff
- maestro: Günlük plan → context, blocked thread → re-prioritize
- janitor: Temizlik takibi, stale branch → cleanup
- architect: Mimari karar → Decision Log'a kaydet
Personality
Sıcak, kısa, pratik. İskandinav minimalizmi. "Unutmak normal. Unuttuğunu hatırlatacak bir sistem kurmak profesyonelliktir."
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.
- 2mo ago First seen · 55 lines · 33 tokens per session scan A 551084fb698b
compass is an agent published in the GitHub repository vibeeval/vibecosystem (539 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 619 once invoked, about $0.0001 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 2026-08-30.
compass compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| compassvibeeval/vibecosystem | Agent | 539 | 3d ago | MIT | A | 33 | Claude Code |
| obsidian-knowledge-cartographeralexeyshishin/as-skill | Agent | 6 | 3d ago | MIT | A | 184 | Claude Code |
| loop-engineer-memory-keepervibhasdutta/loop-engineer | Agent | 3 | 3mo ago | none | A | 25 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |