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 instructions/eliornl/rolemule/claude-mdgit clone --depth 1 https://github.com/eliornl/rolemuleWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/eliornl/rolemule/claude-md)<a href="https://agentmods.dev/instructions/eliornl/rolemule/claude-md"><img src="https://agentmods.dev/badge/instructions/eliornl/rolemule/claude-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.02528 | $0.02528 |
| Opus 5 | $0.01264 | $0.01264 |
| Sonnet 5 | $0.00506 | $0.00506 |
| Haiku 4.5 | $0.00253 | $0.00253 |
Grade A, and why
rolemule CLAUDE.md 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 3d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RoleMule — Claude Code Rules Index
Product name: RoleMule (repo folder: rolemule).
All detailed rules live in .claude/rules/. Read the relevant file(s) before working in that area. Never load all files — only pull what the task needs.
Rule Files
| File | Read when... |
|---|---|
.claude/rules/rolemule-core.mdc |
any task — app name, APIError/ErrorCode (CFG_6001, RES_3002, content fingerprint NFKC + utils/application_dedupe.py, post-start duplicate / uq_user_job_company), POST /workflow/start job file (.pdf/.txt/.docx, 5 MB), background tasks, workflow failure (no partial outputs, dashboard list join), route prefixes |
.claude/rules/python-conventions.mdc |
writing or editing any Python file |
.claude/rules/database-patterns.mdc |
touching models, migrations, JSONB fields, SQLAlchemy queries |
.claude/rules/auth-patterns.mdc |
auth endpoints, JWT, login, registration, token revocation, lockout |
.claude/rules/security-python.mdc |
any security-sensitive Python code (XSS, file upload, tokens, secrets) |
.claude/rules/codeql-security-scanning.mdc |
CodeQL CI, log sanitization, secret scanning test keys, Pydantic field_validator, extension entity decode |
.claude/rules/security-middleware.mdc |
middleware, CORS, CSP, .is-hidden, maintenance mode |
.claude/rules/settings-and-env.mdc |
env vars, get_settings(), .env, ENCRYPTION_KEY |
.claude/rules/llm-integration.mdc |
Multi-provider LLM (get_llm_client), per-user BYOK (Gemini/OpenAI/Anthropic/Ollama), model allowlists in utils/llm/models.py, grounding, CFG_6001, DEFAULT_MAX_TOKENS (16k), generate_stream / SpeakFieldStreamer |
.claude/rules/agent-patterns.mdc |
workflow agents (any agent failure fails the workflow), standalone interview prep + CV optimizer + Practice Interview + Hiring Outreach, workflow_preferences, BYOK model override, Company Research — _has_usable_company_name / unnamed-posting / disambiguation / staffing / research_quality |
.claude/rules/interview-prep-feature.mdc |
interview prep agent, background task, Redis lock, rate limit (static Interview tab — not Practice Interview) |
.claude/rules/mock-interview-feature.mdc |
Mock Session / Practice Interview (HR/Pro/Manager), duration timer, browser STT/TTS, BYOK, speak streaming / speak_delta, ws-guard |
.claude/rules/hiring-outreach-feature.mdc |
Hiring Outreach — public web contacts + copy-only drafts, hiring_outreach JSONB, Redis lock, WS hiring_outreach_*, 10th Outreach tab |
.claude/rules/cv-optimizer-feature.mdc |
CV Optimizer loop, API, cache, WebSocket, application detail tab |
.claude/rules/career-tools.mdc |
6 career tool agents, endpoints, rate limits, output schemas, copy button |
.claude/rules/caching-redis.mdc |
cache TTLs, Redis helpers, job-analysis key (up to 50k chars of text), rate limiting, auth-specific keys |
.claude/rules/websocket-patterns.mdc |
WebSocket endpoints, connection limits, broadcast helpers, mock interview speak_delta + client session filter |
.claude/rules/logging-patterns.mdc |
StructuredLogger, sanitize_log_value() / mask_email(), redaction, exc_info=True, bulk-script safety |
.claude/rules/google-oauth.mdc |
OAuth flow, CSRF state in Redis, exchange-code pattern, open-redirect |
.claude/rules/email-and-misc-utils.mdc |
Gmail SMTP, resume parser, BYOK encryption |
.claude/rules/frontend-js-strict.mdc |
any ui/src/**/*.ts — TypeScript strict, null safety, event delegation, no style= attrs |
.claude/rules/landing-page.mdc |
index.html, landing page sections, screenshot showcase |
.claude/rules/dashboard-home.mdc |
dashboard app list, workflow_sessions join (hide workflow-failed), funnel stats formula, search/filter/sort, single-flight loadApplications, EXISTS pagination, toasts (notifyReady c:/f: keys, duplicate headline), isPlaceholderCompanyName / Unknown employer, card CSS, session storage |
.claude/rules/ui-application-detail.mdc |
application detail page, 10-tab layout (Optimize CV + Mock Session + Outreach), View posting link, additional_locations, render functions, isPlaceholderCompanyName / Unknown / About this opportunity, company research notices (research_quality / staffing), CSS classes |
.claude/rules/accessibility.mdc |
any template — WCAG 2.1 AA, heading hierarchy, landmarks, aria |
.claude/rules/analytics-consent-onboarding.mdc |
PostHog, cookie consent, onboarding tour |
.claude/rules/chrome-extension.mdc |
anything inside extension/ — popup vs service-worker submit paths, source_url → job_url, extractPageContent / split-view detail root, dev/prod toggle, autofill, InputMethod.EXTENSION |
.claude/rules/adding-new-features.mdc |
adding a new endpoint, agent, tool, migration, asset, or preference |
.claude/rules/settings-page.mdc |
settings tabs, Preferences, AI Setup, auto-save, account-icon variants |
.claude/rules/frontend-build-pipeline.mdc |
Vite+TS page entries + esbuild CSS, asset_url(), manifest, make build-frontend |
.claude/rules/cli.mdc |
RoleMule CLI — Typer commands, rolemule_client, tests/test_cli/, docs |
.claude/rules/mobile-responsive.mdc |
breakpoints, navbar collapse, scrollable tab bars, mobile utilities |
.claude/rules/unit-testing.mdc |
~300 agent + ~1,050 API + 364 CLI + 6 ASGI CLI integration tests; live_server_helpers; ASGITransport (not TestClient) for CLI ASGI; cov ≥97% includes root test_cv_* |
.claude/rules/e2e-testing.mdc |
~1,380 Playwright specs; CI smoke-only (e2e-smoke); setupAuth, page.route(), JWT/cookie-consent setup |
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.
- 3d ago First seen · 81 lines · 2,528 tokens per session scan A 98805f240ad2
rolemule CLAUDE.md is an instructions file published in the GitHub repository eliornl/rolemule (37 stars, last pushed 4d ago), licensed MIT. It adds 2,528 tokens to every session, about $0.0126 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 instructions, from other repositories
caelo CLAUDE.md
Instructions for AuraVixStudio/caelo, covering claude.md, what this is, the single most important structural fact, architecture and commands.
claude-linkedin-assistant CLAUDE.md
Instructions for FarzamHejaziK/claude-linkedin-assistant, covering claude.md — claude linkedin assistant, what this is, primary workflow, where the docs live (read before acting) and user resume — the source of truth.
ai-tab-optimizer CLAUDE.md
Instructions for eiler2005/ai-tab-optimizer, covering ai tab optimizer — claude code guide, core rules, commands, extension and ai server.
html-anything AGENTS.md
AGENTS.md instructions for nexu-io/html-anything, covering this is not the next.js you know, workspace shape and commands.
geolens CLAUDE.md
Instructions for geolens-io/geolens: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
substack-gateway-oss CLAUDE.md
Instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.