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/adr1an04/erga-mcp/agents-mdgit clone --depth 1 https://github.com/Adr1an04/erga-mcpWhat 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 | $0.00747 | $0.00747 |
| Opus 5 | $0.00374 | $0.00374 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
erga-mcp AGENTS.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 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.
Erga MCP contributor and agent guide
Start here
Read docs/architecture/README.md, use docs/architecture/module-map.md to find the owner, then
route tests with docs/development.md. Use docs/README.md as the documentation index. Inspect the
owning module and its focused tests before editing; do not begin in cli.py or mcp/server.py when
the behavior belongs in a domain package.
Product boundary
Erga is a local-first career assistant. It may organize data, propose edits, and synchronize user-authorized sources. It must not submit applications, send messages, mutate remote mail, or make irreversible account changes without a separate explicit user action.
The standalone CLI and deterministic domain/application modules are the core. MCP, Hermes, Discord, cron, mail, and Obsidian are adapters. Dependency direction is interface → application → domain; core modules must not import an optional interface.
Change routing
| Work | Location |
|---|---|
| MCP schemas/profile policy/tool families | src/erga_mcp/mcp/ |
| MCP composition and transports | src/erga_mcp/mcp/server.py, src/erga_mcp/mcp/transport.py |
| Resume evidence, layout, or generation | src/erga_mcp/resumes/ |
| Projects and Git evidence | src/erga_mcp/portfolio/ |
| Applications and research | src/erga_mcp/applications/ |
| Tracking, contacts, and presentation models | src/erga_mcp/tracking/ |
| Setup, diagnostics, export, and uninstall | src/erga_mcp/operations/ |
| Shared persistence and records | src/erga_mcp/store.py, src/erga_mcp/models.py |
| Optional hosts and providers | src/erga_mcp/integrations/ |
Nested AGENTS.md files refine these rules for MCP, provider adapters, Hermes, and tests. Read the
nearest applicable guide before changing one of those trees.
New reusable behavior belongs in the owning module. New MCP tools belong in a cohesive tool-family module and are registered from the server facade. Do not grow a second monolith.
Privacy and safety
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 · 747 tokens per session scan A 471d06bb8b3b
erga-mcp AGENTS.md is an instructions file published in the GitHub repository Adr1an04/erga-mcp (13 stars, last pushed 4d ago), licensed MIT. It adds 747 tokens to every session, about $0.0037 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
trove AGENTS.md
AGENTS.md instructions for JNHFlow21/trove, covering trove local capability runtime, runtime, safety and required checks.
work-assistant AGENTS.md
AGENTS.md instructions for Wulfgardr/work-assistant, a project described as: Gestione locale e indipendente dal provider della posta per persone e agenti AI.
anytype-ts AGENTS.md
AGENTS.md instructions for anyproto/anytype-ts, covering agents.md, project structure, state management with mobx, electron integration and inter-process communication (ipc).
wet-mcp AGENTS.md
Instructions for n24q02m/wet-mcp, covering agents.md - wet-mcp, cau truc, lenh thuong dung, mise shortcuts and cau hinh quan trong.
proton-mail-bridge-client AGENTS.md
Instructions for googlarz/proton-mail-bridge-client, covering memory context and claude-mem status.
luxembourg-mcp CLAUDE.md
Instructions for amirdaraee/luxembourg-mcp, covering claude.md, commands, hard constraint: zero dependencies, architecture and adding or changing a tool touches five places.