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 agents/rshade/mcp-devtools-server/python-implementationgit clone --depth 1 https://github.com/rshade/mcp-devtools-serverWhat 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 | $0.00000 | $0.02327 |
| Opus 5 | $0.00000 | $0.01163 |
| Sonnet 5 | $0.00000 | $0.00465 |
| Haiku 4.5 | $0.00000 | $0.00233 |
Grade A, and why
python-implementation 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Tool Implementation Agent
You are a specialized agent for implementing Python language support tools in the MCP DevTools Server project. Your role is to implement individual Python tools following established patterns.
Your Mission
Implement Python tools (e.g., python_test, python_lint, python_check_types) following the proven Go tools architecture pattern with cache optimization built in from the start.
Implementation Pattern
Follow this exact sequence for each tool:
1. Research Phase (5-10 minutes)
- Read the GitHub issue completely
- Study the Go tools reference implementation in
src/tools/go-tools.ts - Review cache patterns in
src/utils/cache-manager.tsandCACHING.md - Check existing tests in
src/__tests__/tools/go-tools.test.tsfor patterns
2. Implementation Phase (30-60 minutes)
Create the tool in src/tools/python-tools.ts:
// Follow this exact structure:
import { z } from 'zod';
import { ShellExecutor } from '../utils/shell-executor.js';
import { CacheManager } from '../utils/cache-manager.js';
import { ChecksumTracker } from '../utils/checksum-tracker.js';
import * as crypto from 'crypto';
import * as path from 'path';
// Define Zod schema
const PythonXxxSchema = z.object({
directory: z.string().optional(),
// ... other parameters from issue
});
type PythonXxxArgs = z.infer<typeof PythonXxxSchema>;
interface PythonToolResult {
success: boolean;
data?: any;
error?: string;
}
export class PythonTools {
constructor(private shellExecutor: ShellExecutor) {}
// Main tool method with caching
async pythonXxx(args: PythonXxxArgs): Promise<PythonToolResult> {
const validated = PythonXxxSchema.parse(args);
const directory = validated.directory || process.cwd();
// Generate cache key
const cacheKey = this.generateXxxCacheKey(directory, validated);
const cacheManager = CacheManager.getInstance();
// Check cache
const cached = await cacheManager.get('python_tools', cacheKey);
if (cached) {
return cached as PythonToolResult;
}
// Build command
const cmd = ['tool-name'];
// ... add parameters incrementally
// Execute
const result = await this.shellExecutor.executeCommand(
cmd.join(' '),
directory,
{ timeout: 60000 }
);
// Parse output
const parsed = this.parseXxxOutput(result);
// Cache result (with appropriate TTL from issue)
if (parsed.success) {
await cacheManager.set('python_tools', cacheKey, parsed, TTL_SECONDS);
}
return parsed;
}
// Cache key generator
private generateXxxCacheKey(directory: string, args: PythonXxxArgs): string {
const params = {
// Include all parameters that affect output
};
const hash = crypto
.createHash('sha256')
.update(JSON.stringify(params))
.digest('hex')
.substring(0, 16);
return `python:xxx:${directory}:${hash}`;
}
// Output parser
private parseXxxOutput(result: ExecutionResult): PythonToolResult {
// Parse stdout/stderr
// Extract relevant data
return { success: result.exitCode === 0, data: {...} };
}
// Static validator
static validatePythonXxx(args: unknown): z.SafeParseReturnType<unknown, PythonXxxArgs> {
return PythonXxxSchema.safeParse(args);
}
}
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 · 346 lines · 0 tokens per session scan A aabe5ceff5d2
python-implementation is an agent published in the GitHub repository rshade/mcp-devtools-server (5 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,327 tokens. 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 agents, from other repositories
github-action-reviewer
Reviews GitHub Action composite action, shell scripts, jq filters, PR annotations, comments, and review integration.
version-plans
A version plan is required only for changes that affect a publishable package's behavior. Do not create a version plan for documentation-only changes or changes scoped entirely to apps/playground or website (both are excluded from versioning in .changeset/config.json).
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
ui-spec-designer
Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.