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/reasvyn/docsgrep/code-writingnpx skills add reasvyn/docsgrep --skill code-writinggit clone --depth 1 https://github.com/reasvyn/docsgrepWhat 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 | $0.00021 | $0.00542 |
| Opus 5 | $0.00010 | $0.00271 |
| Sonnet 5 | $0.00004 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
code-writing 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before writing code
- Read
AGENTS.mdfor repo conventions. - Find an existing tool handler that does something similar and use it as a template.
Tool handler pattern
Every tool must return McpToolResponse:
import type { McpToolResponse } from "../types/tools.js";
export async function handleMyTool(args: MyToolArgs): Promise<McpToolResponse> {
try {
const dirPath = validateDirPath(validateStringParam(args.dirPath, "dirPath"));
// ... do work ...
return { content: [{ type: "text", text: JSON.stringify(result, null, 2) })];
} catch (error: any) {
return { content: [{ type: "text", text: error.message }], isError: true };
}
}
BaseTool (for heavier tools)
Extend BaseTool<T> from tools/base.ts when you need built-in concurrency control, logging, and credential masking. Then wrap in a thin function for the registry:
class MyTool extends BaseTool<MyToolArgs> {
protected async run(args: MyToolArgs): Promise<McpToolResponse> {
// ... implementation ...
}
}
export async function handleMyTool(args: MyToolArgs): Promise<McpToolResponse> {
return new MyTool().execute(args);
}
Registration
Add the handler to ToolRegistry in tools/registry.ts. For class-based tools, pass as an override in index.ts.
Tool definitions
Add a JSON Schema entry to src/config/tools.json with name, description, and inputSchema.
Mandatory conventions
- ESM
.jsextensions: every local import MUST end in.js. - No implicit
any: use typed args fromtypes/tools.ts. - Input validation: always call
validateDirPathandvalidateStringParamat entry. - File scanning: use
FileScanner.findFiles()fromtools/base.ts— it handles.gitignore,includePath,excludePath. - App metadata: use
AppInfofromutils/app-info.ts, never hardcode version/name. - Concurrency: if doing IO, acquire/release
operationLimiterfromutils/semaphore.js. - Sensitive data: add new secret fields to
maskSensitiveintools/base.ts.
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 · 61 lines · 21 tokens per session scan A 85ece7bd799c
code-writing is a skill published in the GitHub repository reasvyn/docsgrep (0 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 542 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…