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/plurigrid/asi/captpnpx skills add plurigrid/asi --skill captpgit clone --depth 1 https://github.com/plurigrid/asiWhat 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 | $0.01558 |
| Opus 5 | $0.00000 | $0.00779 |
| Sonnet 5 | $0.00000 | $0.00312 |
| Haiku 4.5 | $0.00000 | $0.00156 |
Grade A, and why
captp 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CapTP: Capability Transfer Protocol
Trit: 0 (ERGODIC - transports capabilities without amplification) Color: #46F27F (Coordinator stream) Source: Spritely Goblins (codeberg.org/spritely/goblins)
Overview
CapTP (Capability Transfer Protocol) enables distributed object programming with capability security. Objects can live anywhere on the network; CapTP abstracts location so programmers focus on object interaction, not protocol architecture.
Core principle: Capabilities are unforgeable references. You can only invoke what you've been given.
Key Concepts
Vats (Actor Containers)
;; Guile Goblins
(define vat (spawn-vat))
(define greeter (vat-spawn vat ^greeter))
| Concept | Description | Trit Mapping |
|---|---|---|
| Vat | Transactional actor container | 0 (ergodic boundary) |
| Actor | Encapsulated object with behavior | +1 (generative) |
| Capability | Unforgeable reference | -1 (constraining) |
Promise Pipelining
;; Don't wait for result - pipeline through promises
(<- (<- alice 'get-friend) 'greet "Hello")
Reduces round-trips: send message to promise, network resolves.
Sturdy vs Live References
| Reference | Persistence | Use Case |
|---|---|---|
| Live | Session only | Active communication |
| Sturdy | Survives restart | Reconnection, storage |
CapTP Message Types
op:deliver-only → Fire-and-forget message
op:deliver → Message expecting response
op:pick → Select from multiple promises
op:abort → Cancel pending operation
op:listen → Subscribe to updates
op:gc → Garbage collection hint
GF(3) Triads
# Core CapTP Bundle
keychain-secure (-1) ⊗ captp (0) ⊗ gay-mcp (+1) = 0 ✓ [Secure Transport]
shadow-goblin (-1) ⊗ captp (0) ⊗ agent-o-rama (+1) = 0 ✓ [Distributed Actors]
polyglot-spi (-1) ⊗ captp (0) ⊗ pulse-mcp-stream (+1) = 0 ✓ [Cross-Lang Objects]
temporal-coalgebra (-1) ⊗ captp (0) ⊗ koopman-generator (+1) = 0 ✓ [State Observation]
# Goblins Integration
three-match (-1) ⊗ captp (0) ⊗ gay-mcp (+1) = 0 ✓ [Colored Capabilities]
sheaf-cohomology (-1) ⊗ captp (0) ⊗ operad-compose (+1) = 0 ✓ [Compositional]
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 · 212 lines · 0 tokens per session scan A 5141026f3b44
captp is a skill published in the GitHub repository plurigrid/asi (61 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,558 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 2026-09-01.
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…