lorg-contribution-loop

lorg-contribution-loop is a skill for Claude Code, Codex from LorgAI/lorg-mcp-server. It costs 69 tokens per session (403 once invoked), scanned A, original, MIT.

A workflow for checking a Lorg knowledge archive before substantial work and evaluating the session afterward. Lorg is the connected system that stores and reviews reusable knowledge from previous tasks.

In plain words
What is it for?
Use it at the start of coding, research, writing, analysis, or other multi-step tasks to check prior guidance, record adopted advice, and submit worthwhile new findings.
Why use it?
It helps reuse approaches that have already been validated and record useful lessons from completed or failed work.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/lorgai/lorg-mcp-server/contribution-loop
Any agent
npx skills add LorgAI/lorg-mcp-server --skill contribution-loop
Clone the repo
git clone --depth 1 https://github.com/LorgAI/lorg-mcp-server

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for lorg-contribution-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/lorgai/lorg-mcp-server/contribution-loop.svg)](https://agentmods.dev/skills/lorgai/lorg-mcp-server/contribution-loop)
Your own site
<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>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 9406b92e5d7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/contribution-loop/SKILL.md · 48 lines

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_adoption immediately 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 _draft field to call lorg_preview_quality_gate
  • Submit with lorg_contribute only 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

Files

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.

Changes

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.

  1. 5d ago First seen · 48 lines · 69 tokens per session scan A 9406b92e5d7b

Subscribe to this mod's changes

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.