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 commands/wittyreference/twilio-claude-plugin/prototypegit clone --depth 1 https://github.com/wittyreference/twilio-claude-pluginWhat 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 | $0.00029 | $0.00728 |
| Opus 5 | $0.00015 | $0.00364 |
| Sonnet 5 | $0.00006 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
prototype 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 yesterday.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype / Spike
You are running a quick prototype (spike) to explore unknowns before committing to a specification and TDD cycle. This is explicitly sloppy — no tests, no docs, no production quality required.
Purpose
Reveal how a Twilio API, integration, or pattern actually behaves before investing in a full implementation. The output is knowledge, not code.
When This Phase Is Needed
The /architect subagent should recommend prototyping when:
- Using a Twilio API for the first time in this project
- The API has known behavioral quirks (e.g.,
<Pay>, Media Streams, SIP Trunking) - The integration involves multiple services interacting in ways we haven't tested
- Documentation is ambiguous or incomplete about a specific behavior
- The feature involves real-time protocols (WebSocket, DTMF, conference events)
What to Do
- Identify the unknowns — What specific questions need answers?
- Build the minimum — Smallest possible code that exercises the unknown behavior
- Test against live Twilio — Use real API calls, not assumptions from docs
- Record what you learned — Write a short "Spike Results" note
Rules
- No tests required — This is throwaway code
- No documentation required — Just the spike results note
- No code review — Speed over quality
- No deployment — Use
twilio-runlocally or direct API calls - DO clean up — Delete or
.gitignoreprototype files when done - DO use real Twilio APIs — Never simulate or mock behavior you're trying to understand
Output Format
## Spike Results: [Topic]
### Questions Investigated
1. [Question 1]
2. [Question 2]
### Findings
1. [Answer to Q1 — with evidence]
2. [Answer to Q2 — with evidence]
### Surprises / Gotchas
- [Anything unexpected that should inform the spec]
### Recommendation
[PROCEED to /spec | REDESIGN the approach | ESCALATE to user]
### Prototype Code Location
[Path to throwaway code, or "deleted" if cleaned up]
After the Spike
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.
- yesterday First seen · 84 lines · 29 tokens per session scan A 13defe32e16c
prototype is a command published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 728 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.