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/wittyreference/twilio-claude-plugin/context-engineeringnpx skills add wittyreference/twilio-claude-plugin --skill context-engineeringgit 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 | $0.00012 | $0.00881 |
| Opus 5 | $0.00006 | $0.00441 |
| Sonnet 5 | $0.00002 | $0.00176 |
| Haiku 4.5 | $0.00001 | $0.00088 |
Grade A, and why
context-engineering 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: context-engineering description: Context management and compression techniques. Use when optimizing context window usage, managing large sessions, or applying compression strategies for Twilio development.
Context Engineering for Twilio Development
Unified context management skill — fundamentals, compression techniques, and session optimization.
Quick Reference: Compression Ratios
| Content Type | Ratio | Preserve | Drop |
|---|---|---|---|
| TwiML | 5:1 | Verb sequence, actions, key attrs | XML boilerplate, default attrs |
| Webhook payload | 4:1 | From/To, SID, status, body/digits | AccountSid, ApiVersion, geo fields |
| Test output (pass) | 10:1 | Count by category | Individual test names |
| Test output (fail) | 3:1 | Test name, expected vs received | Stack traces |
| Error logs | 5:1 | Error code, URL, count, timeframe | Duplicate entries |
| Conversation history | 8:1 | Decisions, files changed, current state | Implementation details |
When to Compress
- TwiML responses > 20 lines →
Voice: Say(x) → Gather(y) → Dial(z) - Webhook payloads > 5 fields →
SMS from +1555...4567: "Hello" (SMxxx) - Test output > 50 lines →
Tests: 12 passed (voice: 4, messaging: 4, verify: 4) - Error logs with repeats →
Error 11200: /voice/incoming 502 — 5 occurrences in 2 min - Session history > 10 exchanges → summarize progress, drop resolved threads
Context Budget
| Task Type | Recommended Load |
|---|---|
| Simple bug fix | 1 file + error message |
| New function | Pattern file + domain CLAUDE.md |
| Feature with tests | 2-3 files max |
| Complex refactor | 4-5 files, summarized |
| Full workflow | Use plan mode, load per-phase |
Loading Strategy
Always loaded (~2,900 tokens / 1.4% of 200K):
- Root CLAUDE.md, CLAUDE.md, MEMORY.md
Load on demand (when entering domain):
- Domain CLAUDE.md (e.g.,
CLAUDE.md) - Similar existing function as pattern
- Relevant test file
Avoid loading:
- CLAUDE.md files for domains you're not touching
- Full test suites (just the relevant test)
- Historical git logs
- Passing test output (compress to counts)
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 · 96 lines · 12 tokens per session scan A 8d01157fef5c
context-engineering is a skill published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 881 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 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.