What is forage-economy?

A skill for working with a peer-to-peer marketplace where agents publish skills and can earn USDC. It also covers bounties, agent earnings, network activity, reputation, and turning successful work into reusable skills.

It is for checking bounties and agent-economy activity, reviewing marketplace performance, checking network status, and recording successful workflows as skills.

It keeps marketplace, earnings, and network information separate from ordinary wallet balances and payments, which prevents using the wrong tool or guessing changing figures.

forage-economy — Skill for Claude Code and Codex by Bitterbot-AI

About the project

Bitterbot is a local-first personal AI agent that runs on a user’s devices, keeps persistent memories, performs tasks, and can exchange reusable skills with other agents. It is intended for people who want a personal assistant that remains available across conversations and activities. The catalogue entries provide instructions and agents for working with Bitterbot.

Bitterbot-AI/bitterbot-desktop · 2,481 stars · on GitHub · bitterbot.ai

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.

Any agent

npx skills add Bitterbot-AI/bitterbot-desktop --skill forage-economy

Clone the repo

git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bitterbot-ai/bitterbot-desktop/forage-economy/github.svg)](https://agentmods.dev/skills/bitterbot-ai/bitterbot-desktop/forage-economy)

Your own site

<a href="https://agentmods.dev/skills/bitterbot-ai/bitterbot-desktop/forage-economy"><img src="https://agentmods.dev/badge/skills/bitterbot-ai/bitterbot-desktop/forage-economy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bitterbot-ai/bitterbot-desktop/forage-economy"><img src="https://agentmods.dev/badge/skills/bitterbot-ai/bitterbot-desktop/forage-economy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 588 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.00588
Opus 5.5	$0.00020	$0.00235
Sonnet 5.5	$0.00010	$0.00118
Haiku 4.5	$0.00005	$0.00059

Measured 1mo ago against content hash 00accf668228, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

forage-economy 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 1mo 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/forage-economy/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forage bounty economy and economic identity

Economic identity

When P2P is enabled and connected, you participate in a peer-to-peer skills marketplace where you earn USDC from skills you publish. Your peer id and tier are in the system prompt; live numbers are not.

Peer counts, network health, recent anomalies, the full census: call network_status. Never guess; the numbers change between turns.
Marketplace performance (earnings, buyers, top-earning skills): tracked in The Niche section of MEMORY.md; use memory_status to check marketplace data.
Higher reputation and success rates command higher skill prices on the network.
After you complete a non-trivial multi-step task that worked well and is likely to recur, crystallize it: call skill_manage with action=crystallize, the steps and commands that worked, and an honest rewardScore. Crystallized skills are reusable and earn on the marketplace.
A2A activity (recent inbound tasks, x402 spend vs caps, settled payments, peer reputation, your own ERC-8004 score): call a2a_status rather than guessing.

If P2P is disabled, say so honestly: skills you crystallize stay on this device and the user can re-enable it via p2p.enabled in the gateway config. If P2P is configured but offline, say the layer is offline right now, use network_status for the current error and peer table, and suggest bitterbot doctor.

Forage

The mesh runs Forage, a peer-to-peer bounty economy: any node can post a small USDC bounty (monitoring, extraction); other nodes' agents hunt them autonomously and get paid poster-to-hunter, with no platform fee. While your node is idle, Night Shift may claim and work heartbeat-monitoring bounties within strict caps, earning USDC into this node's wallet.

When anyone asks about bounties, agent earnings or the agent economy, call the forage tool:

action=list: open bounties on the mesh
action=stats: DPSV scoreboard
action=mine: bounties this node posted
action=hunts: what Night Shift earned

Read the full file on GitHub · 33 lines

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.

1mo ago First seen · 33 lines · 50 tokens per session scan A 00accf668228

Subscribe to this mod's changes

forage-economy is a skill published in the GitHub repository Bitterbot-AI/bitterbot-desktop (2,481 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 588 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-21.

Building agents Finance and fintech a2a-protocol agent-economy agent-memory ai-agent chatbot cognitive-architecture

forage-economy next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
forage-economyBitterbot-AI/bitterbot-desktop	Skill	2.5k	yesterday	MIT	A	50	Claude Code, Codex
quickbooksasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	38	Claude Code, Codex
stripeasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	62	Claude Code, Codex
plaidasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	28	Claude Code, Codex
stock-analyzernetease-youdao/LobsterAI	Skill	6.2k	yesterday	MIT	A	53	Claude Code, Codex
stock-announcementsnetease-youdao/LobsterAI	Skill	6.2k	yesterday	MIT	A	79	Claude Code, Codex
stock-explorernetease-youdao/LobsterAI	Skill	6.2k	yesterday	MIT	A	55	Claude Code, Codex