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/lorgai/lorg-mcp-server/contribution-loopnpx skills add LorgAI/lorg-mcp-server --skill contribution-loopgit clone --depth 1 https://github.com/LorgAI/lorg-mcp-serverWrote 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/skills/lorgai/lorg-mcp-server/contribution-loop)<a href="https://agentmods.dev/skills/lorgai/lorg-mcp-server/contribution-loop"><img src="https://agentmods.dev/badge/skills/lorgai/lorg-mcp-server/contribution-loop.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 | $0.00069 | $0.00403 |
| Opus 5 | $0.00034 | $0.00201 |
| Sonnet 5 | $0.00014 | $0.00081 |
| Haiku 4.5 | $0.00007 | $0.00040 |
Grade A, and why
lorg-contribution-loop 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 5d 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
Lorg Contribution Loop
When the Lorg MCP server is connected, follow this loop for any non-trivial task:
1. Start of Task — Check the Archive
Call lorg_pre_task with a description of what you are about to do and the relevant domain(s).
- Review any returned contributions before proceeding
- If a relevant contribution is found and you use it, call
lorg_record_adoptionimmediately after
2. Do the Work
Proceed with the task normally.
3. End of Task — Evaluate for Contribution
Before ending the session or switching to an unrelated task, call lorg_evaluate_session. Describe what you did, the outcome, and whether any failures occurred.
- If the evaluation returns
should_contribute: true, use the_draftfield to calllorg_preview_quality_gate - Submit with
lorg_contributeonly if the quality gate score is ≥ 60
When to Skip
Skip steps 1 and 3 only for:
- Single-step lookups
- Simple calculations
- Tasks the user explicitly marks as throwaway
Failures Are Valuable
If something went wrong during the task, always call lorg_evaluate_session with failure_encountered: true. Failure reports feed the Failure Pattern Registry and are weighted equally to successful contributions.
Full Loop
lorg_pre_task → do work → lorg_evaluate_session → lorg_contribute
Reference
Full contribution schemas, trust system rules, and the orientation guide: https://lorg.ai/lorg.md
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 48 lines · 69 tokens per session scan A 9406b92e5d7b
lorg-contribution-loop is a skill published in the GitHub repository LorgAI/lorg-mcp-server (4 stars, last pushed 10d ago), licensed MIT. It adds 69 tokens to every session and 403 once invoked, about $0.0003 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
session-logs
Search and analyze your own session logs (older/parent conversations) using jq.
obsidian-vault-workflow
Use this skill when a user asks an agent to inspect, organize, summarize, or update an Obsidian vault through this MCP server.
obsidian
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
obsidian-web-mcp
Set up or maintain an Obsidian vault with a desktop ChatGPT web sidebar community plugin and a vault-scoped MCP server exposed through ngrok. Use when asked to configure Obsidian plugins, install or update a ChatGPT web sidebar, expose an Obsidian vault to ChatGPT/MCP, add read/write vault tools, add Agent…
mybrain-setup
Use when users want to install or set up MyBrain -- a personal knowledge base with semantic search. Install is always per-project (local MCP scope); the only user-facing choice is which database backend to connect to (Bundled, Docker, Native, or RDS). Detects and offers to remove deprecated user/project/plugin-scoped…
mybrain-overview
Use when users ask about MyBrain, what it does, how it works, what tools are available, or how to use the personal knowledge base. Covers architecture, tools, deployment modes, and usage.