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/suuus/ape-context/context-installnpx skills add suuus/ape-context --skill context-installgit clone --depth 1 https://github.com/suuus/ape-contextWhat 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 | $0.00639 |
| Opus 5 | $0.00006 | $0.00319 |
| Sonnet 5 | $0.00002 | $0.00128 |
| Haiku 4.5 | $0.00001 | $0.00064 |
Grade A, and why
context-install 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install the approved MCP servers by writing their configuration to .mcp.json in the project's root directory (the current working directory).
Process
- Read the existing
.mcp.jsonin the working directory if it exists (preserve existing entries) - If no
.mcp.jsonexists, create one - For each approved MCP server from the review phase:
- Add the entry to the
mcpServersobject - Use the standard format — both
typeandtoolsare required:{ "mcpServers": { "server-name": { "command": "npx", "args": ["-y", "@vendor/mcp-server@latest"], "type": "local", "tools": ["*"] } } } - Report: ✅ Added {server-name} or ❌ Failed: {reason}
- Add the entry to the
- Write the updated
.mcp.jsonusing the edit or create tool - Do NOT run npm install — just write the config. The MCP server will be fetched on first use by npx.
Critical format requirements
- Every entry MUST have
"type": "local"— without it the SDK won't discover the server - Every entry MUST have a
"tools"field — without it no tools are exposed
Tool scoping
Retrieve scoping decisions from the session store:
SELECT value FROM session_state WHERE key = 'scoping_decisions';
Fallback chain if session state is empty:
- Check conversation context for Phase 2 (Discover) output
- If neither available, default to
"tools": ["*"]for all servers and inform the user: "No scoping decisions found from Phase 2 — installing with full access. Run/context-discoverfirst to set read-only scoping, or restrict thetoolslist in.mcp.jsonmanually."
Apply the retrieved scoping decisions:
- Read+Write:
"tools": ["*"] - Read-only: scope to specific get/search/list tools for that server, using a concrete allowlist. If the exact read-only tool list isn't known for a server, keep
"tools": ["*"]and inform the user: "Read-only scoping isn't available for {server} yet — installing with full access. You can restrict the tools list manually later."
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 · 71 lines · 12 tokens per session scan A 7807cea8056c
context-install is a skill published in the GitHub repository suuus/ape-context (2 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 639 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.
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…