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/fradser/dotclaude/get-contextnpx skills add FradSer/dotclaude --skill get-contextgit clone --depth 1 https://github.com/FradSer/dotclaudeWhat 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 | $0.00045 | $0.00545 |
| Opus 5 | $0.00023 | $0.00272 |
| Sonnet 5 | $0.00009 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
get-context 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.
What it actually says
get-context
Launch a code-context:context-researcher agent that executes the full workflow in an isolated context. The input is arbitrary: a natural-language question, a repo slug, a library name, or several of these at once.
Argument parsing
- Split
$ARGUMENTSinto positional targets and the optional--methodflag.--method=accepts a comma-separated list fromdeepwiki,context7,exa,clone,web,all. Default:all.- Quoted strings are one target:
"compare zustand vs jotai state management"is a single natural-language query. - Multiple positional tokens are multiple targets:
facebook/react zustand= two targets.
- Classify each target:
- GitHub slug (
owner/repo) or git URL → repo target (DeepWiki / clone). - Bare name matching a known package ecosystem (
react,fastapi,next) or with a version hint (react@18) → library target (Context7). - Anything else (a question, a comparison, a concept) → natural-language target (Exa / web search).
- GitHub slug (
- Empty input: read dependency manifests in the current working directory (
package.json,go.mod,pyproject.toml,Cargo.toml) and use detected dependencies as targets.
Prompt template
Pass the parsed targets and method list to the agent verbatim — do not pre-resolve them in the main context.
Code context request.
Targets (classify each as repo / library / natural-language query):
<positional targets, one per line; or "auto-detect from local dependency manifests" if empty>
Methods to use (in priority order; "all" = let agent choose per target):
<comma-separated method list, default "all">
Local context already known: <one line on what the cwd already contains, or "none">
Execute
Launch code-context:context-researcher using the prompt template above. The agent returns a synthesized summary; the main context stays clean regardless of lookup volume.
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 · 44 lines · 45 tokens per session scan A 6dc2a53022d8
get-context is a skill published in the GitHub repository FradSer/dotclaude (588 stars, last pushed 21d ago), licensed MIT. It adds 45 tokens to every session and 545 once invoked, about $0.0002 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 2026-08-30.
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.