What is sancho-update?

A skill guide for Sancho Fetch, a local tool that checks, previews, applies, and rolls back managed updates.

Use it to inspect available updates, review them, apply them, roll them back, and handle files customised by the user.

It provides a defined update process that protects personal workspace changes and explains what will change.

How panth-net/sancho-fetch configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to panth-net/sancho-fetch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/panth-net/sancho-fetch/master/.agents/skills/sancho-update/SKILL.md

Clone the repo

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

Made for: Claude Code.

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/panth-net/sancho-fetch/sancho-update/github.svg)](https://agentmods.dev/skills/panth-net/sancho-fetch/sancho-update)

Your own site

<a href="https://agentmods.dev/skills/panth-net/sancho-fetch/sancho-update"><img src="https://agentmods.dev/badge/skills/panth-net/sancho-fetch/sancho-update/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/panth-net/sancho-fetch/sancho-update"><img src="https://agentmods.dev/badge/skills/panth-net/sancho-fetch/sancho-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,390 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	$0.00025	$0.01390
Opus 5	$0.00013	$0.00695
Sonnet 5	$0.00005	$0.00278
Haiku 4.5	$0.00003	$0.00139

Measured 10d ago against content hash 530f453da836, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sancho-update 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 10d 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.

.agents/skills/sancho-update/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sancho Fetch update skill

You are operating the Sancho update flow. Sancho provides deterministic check, preview, apply, and rollback primitives. The agent explains changes, preserves user work, and migrates deliberate managed-file edits into custom/<type>/<module>/ before applying upstream updates.

Read CLAUDE.md or AGENTS.md before doing anything. Sancho never requires raw Git commands. How new versions arrive depends on package.install_source from sancho update check:

"package" (the normal case -- installed from PyPI): you run uv tool upgrade sancho-fetch, which pulls the newest release. No folder, no Git, nothing for the user to download.
"checkout" (developers working from the repository): the user pulls new commits with GitHub Desktop, then you reinstall the sancho command from that checkout when update check says so.

Either way, sancho update apply migrates the workspace afterwards.

Required Flow

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 confirm 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. 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.
Run sancho update check --workspace <ws> --json. Read every relevant field: package.install_source, package.reinstall_needed, modules[].status, files_with_local_edits, custom_override_active, env_present, gitignore_covers_generated, is_git_repo, git_dirty, and personal_paths_touched_by_update.
If package.reinstall_needed is true, the installed sancho command is out of date. Run the exact package.reinstall_command yourself -- for install_source == "package" that is uv tool upgrade sancho-fetch; for "checkout" it is an uv tool install --force ... on the checkout path. Then re-run sancho update check and continue with the fresh output.
Run sancho update preview --workspace <ws> --json before any apply. For a single module, pass the module ID after preview. Inspect risk_level, recommended_action, files_to_replace, files_with_local_edits, and personal_paths_touched.
Optionally run git status for read-only context. Never run git pull, git fetch, git reset, git clean, git checkout --, force-push, or any destructive Git command.
For each module with files_with_local_edits, inspect the edited files. If the edit looks intentional, propose moving it into custom/<type>/<module>/ before applying and record that with sancho repair note --module <id> --summary "Migrated <file> into custom override before update". If it looks accidental, ask the user before discarding it.
Explain what will change in module-level language. Include updated modules, skipped modules, local edits, active custom overrides, and any risk.
Ask before applying unless the user explicitly requested a safe apply.
Run sancho update apply --workspace <ws> --json. Use --allow-local-edits only when the user approved. Record backup_id, backup_dir, applied/skipped modules, changed paths, and rollback_command.
Run sancho doctor --workspace <ws> --json after apply.
Read logs/update-log.jsonl and update-backups/<backup_id>/update-result.md before claiming success.
Summarize updated, skipped, and preserved items. Include the rollback command.

Read the full file on GitHub · 104 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.

10d ago First seen · 104 lines · 25 tokens per session scan A 530f453da836

Subscribe to this mod's changes

sancho-update is a skill published in the GitHub repository panth-net/sancho-fetch (0 stars, last pushed 13d ago), licensed Apache-2.0. It adds 25 tokens to every session and 1,390 once invoked, about $0.0001 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.

Git and workflow

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

nvca-chart-release

Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.

NVIDIA/nvcf · 61 tokens

sancho-fetch: Skill for Claude Code