What is sancho-fetch AGENTS.md?

A set of instructions for Sancho Fetch, a local-first data library and command-line tool. It explains how coding agents should work with its managed files, fetched records, logs, and exports.

Use it when working in the Sancho Fetch repository. It covers initial checks, the project’s folder structure, operating modes, and keeping related instruction files aligned.

It helps agents follow the repository’s rules and keep source instructions, personal work, fetched data, and derived results organised.

sancho-fetch AGENTS.md — Instructions file for Codex and OpenCode by panth-net: A set of instructions for Sancho Fetch, a local-first…

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 instructions/panth-net/sancho-fetch/agents-md

Clone the repo

git clone --depth 1 https://github.com/panth-net/sancho-fetch

Made for: Codex, OpenCode.

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/instructions/panth-net/sancho-fetch/agents-md.svg)](https://agentmods.dev/instructions/panth-net/sancho-fetch/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/panth-net/sancho-fetch/agents-md"><img src="https://agentmods.dev/badge/instructions/panth-net/sancho-fetch/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,125 This file is loaded in full into every session.

When invoked 2,125 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02125	$0.02125
Opus 5	$0.01063	$0.01063
Sonnet 5	$0.00425	$0.00425
Haiku 4.5	$0.00213	$0.00213

Measured 5d ago against content hash 2bfa32bad81c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

sancho-fetch 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

sancho-fetch CLAUDE.md — 100% identical, 2 lines differ

AGENTS.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md -- Sancho Fetch agent guidance

This root guide is intentionally shared by Claude, Codex, and other agents. Keep CLAUDE.md, AGENTS.md, README_ALL_INSTRUCTIONS.md, and src/sancho/templates/agent_skills/** aligned when changing operator rules.

Read this before doing anything in this repo. The user is often not a coder. Default to plain English unless sancho mode --json reports {"developer_mode": true} or the user asks for technical detail.

What Sancho Is

Sancho Fetch is a local-first data library. After setup, the visible sancho-fetch/ folder contains sancho-workspace/ with managed modules in source/**, personal work in custom/** and playbooks/**, fetched records in fetched-data/**, derived work in analysis-data/**, exports in outputs/**, logs in logs/**, and update backups in update-backups/**. The CLI is sancho.

Sancho produces inspectable facts: paths, manifests, cache status, logs, repair packets, update previews, and exports. The agent reasons about plans, explains changes, chooses bounded fetch units, and migrates user edits when needed. Sancho is not the planner.

First Steps

Check mode before replying with sancho mode --json. If the command is missing or fails during first setup, default to developer mode off and use plain English. Do not open or read .env just to determine mode.
Run sancho paths --json to find the active workspace. If the payload contains update_hint, relay it to the user in one plain sentence before continuing. If the sancho command is missing, fails, or lacks current commands such as setup, paths, ready, or mode, and terminal access is available, do the setup work yourself: run uv tool install sancho-fetch, then sancho setup --json (or use --path <folder> --switch-workspace only when the user explicitly wants to change an existing registered workspace). (Working from a source checkout instead? Run installers\setup.bat on Windows or bash installers/setup.sh on macOS/Linux from the repo root.) Then run sancho ready --json and retry sancho paths --json. If workspace_source == "none", run setup or sancho library register <path-to-workspace-folder> yourself. Only ask the user for help when the OS blocks execution, permissions fail, or an installer window requires human approval.
Use sancho find sources "<text>" --json to pick modules; sancho inventory --json lists the full catalog when you need to browse. Never guess module IDs, request keys, or paths.
For fetches, follow the installed Sancho skill. Source copies live in src/sancho/templates/agent_skills/. Confirm success from the run JSON (status, cache_status, row_count); read sancho log tail --json --limit 5 --module <id> for playbooks or failures.
For updates, follow the installed Sancho update skill. Never update managed modules through raw Git.

Read the full file on GitHub · 140 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.

5d ago First seen · 140 lines · 2,125 tokens per session scan A 2bfa32bad81c

Subscribe to this mod's changes

sancho-fetch AGENTS.md is an instructions file published in the GitHub repository panth-net/sancho-fetch (0 stars, last pushed 8d ago), licensed Apache-2.0. It adds 2,125 tokens to every session, about $0.0106 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.

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

sancho-fetch AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

How it starts

AGENTS.md -- Sancho Fetch agent guidance

What Sancho Is

First Steps

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

spec-kit AGENTS.md

next.js AGENTS.md

codex AGENTS.md

langchain AGENTS.md

vscode oss-third-party-notices.instructions.md