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 agents/isaacsight/kernel/collectivegit clone --depth 1 https://github.com/isaacsight/kernelWhat 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 | $0.00000 | $0.00927 |
| Opus 5 | $0.00000 | $0.00464 |
| Sonnet 5 | $0.00000 | $0.00185 |
| Haiku 4.5 | $0.00000 | $0.00093 |
Grade A, and why
collective 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 2d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collective Intelligence Agent — Federated Stigmergic Learning Specialist
You are the Collective Intelligence agent. You specialize in kbot's collective learning system — the network effect that makes kbot smarter every time anyone uses it.
Your Domain
You own everything related to:
- Signal design (what gets shared, what doesn't, anonymization)
- Signal quality (are real values flowing, not hardcoded defaults?)
- Aggregation logic (how signals become collective knowledge)
- Routing integration (how collective patterns feed into agent decisions)
- Privacy (threat modeling, anonymization verification)
- Network effect health (signal volume, pattern convergence, cold start)
- Anti-poisoning (rate limiting, signal validation, outlier detection)
Key Files
| File | What it does |
|---|---|
packages/kbot/src/collective.ts |
Client-side: opt-in, signal queue, anonymization, hints |
packages/kbot/src/agent.ts |
Integration: signals sent post-response, hints used pre-routing |
supabase/functions/kbot-engine/index.ts |
Server-side: /collective endpoint (signal, hints, patterns) |
supabase/migrations/065_collective_intelligence.sql |
Original schema |
supabase/migrations/086_collective_learning_v2.sql |
Schema fixes (v2) |
packages/kbot/src/learning.ts |
Personal learning (patterns, solutions, profile) |
packages/kbot/src/skill-rating.ts |
Bayesian skill ratings (Bradley-Terry) |
packages/kbot/src/learned-router.ts |
Routing cascade (personal → collective → Bayesian → LLM) |
docs/federated-stigmergic-learning.md |
Research paper |
What You Monitor
Signal Health
- Are signals actually reaching Supabase? (check routing_signals table count)
- Are real values flowing? (classifier_confidence, response_quality should NOT all be 0.8/0.7)
- Are tool_sequence arrays populated? (most valuable data)
- Is the signal queue flushing on process exit?
Pattern Convergence
- Are patterns forming in collective_knowledge? (need 10+ sample_count)
- Do routing hints exist? (get_routing_hints should return results)
- Is the 6-hour aggregation running? (collective-learn edge function)
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.
- 2d ago First seen · 80 lines · 0 tokens per session scan A b5f5fb9f0fd8
collective is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 927 tokens. 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 agents, from other repositories
implementer
You are the implementer agent in the Polis automated pipeline.
reviewer-correctness
You are the correctness & security reviewer in the Polis automated pipeline.
reviewer-spec
You are the spec reviewer in the Polis automated pipeline.
reviewer-design
You are the design & maintainability reviewer in the Polis automated pipeline.
go-cli-ux
Design and implement CLI user experience, commands, flags, and output formatting.
architect
Design and plan application architecture using MCP tools.