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 skills add john-data-chen/hermes-agent-backup --skill package-upgradegit clone --depth 1 https://github.com/john-data-chen/hermes-agent-backupWrote 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/john-data-chen/hermes-agent-backup/package-upgrade)<a href="https://agentmods.dev/skills/john-data-chen/hermes-agent-backup/package-upgrade"><img src="https://agentmods.dev/badge/skills/john-data-chen/hermes-agent-backup/package-upgrade/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.
<a href="https://agentmods.dev/skills/john-data-chen/hermes-agent-backup/package-upgrade"><img src="https://agentmods.dev/badge/skills/john-data-chen/hermes-agent-backup/package-upgrade.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00028 | $0.01604 |
| Opus 5.5 | $0.00011 | $0.00642 |
| Sonnet 5.5 | $0.00006 | $0.00321 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
package-upgrade 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Package Upgrade Workflow
Batch-upgrade npm packages across multiple repos using pnpm.
Prerequisites
- All repos use pnpm as package manager
- GitHub CLI (
gh) or API access for opening PRs - Repos live under
~/projects/
Workflow (MANDATORY ORDER)
For each repo:
1. Prepare branch
cd ~/projects/<repo>
git checkout main
git pull
git checkout -b feat/john/update-packages-YYYYMMDD
If git checkout main fails due to uncommitted changes, stash first:
git stash
git checkout main
git pull
git checkout -b feat/john/update-packages-YYYYMMDD
Leave the stash on the old branch — the user can pop it when they return.
NEVER modify main directly. Always create a feature branch and open a PR.
2. Run upgrade
pnpm up -r --latest
If the upgrade fails (e.g. a package's latest version has a broken transitive dep), see the "Handling broken upstream deps" section in Pitfalls below.
3. Enforce version caps
After upgrade, check and revert these packages if they were bumped beyond the allowed range:
| Package | Cap | Where |
|---|---|---|
@types/node |
latest 24.x.x (e.g. ^24.13.2, not ^24.0.0) |
package.json or pnpm-workspace.yaml (catalog) |
@typescript/native-preview |
"beta" — do NOT upgrade |
package.json or pnpm-workspace.yaml (catalog) |
Revert with sed or manual edit, then confirm with grep.
4. Expo mobile (turborepo-starter-kit only)
For turborepo-starter-kit, the apps/mobile workspace uses Expo and requires a separate upgrade step:
pnpm mobile:expo:upgrade
Run this after the general pnpm up -r --latest and version cap enforcement, but before pnpm install.
5. Install
pnpm install
This regenerates the lockfile after any manual version reverts.
6. Verify
Run the project's verification suite to confirm nothing broke. Read the project's AGENTS.md for the exact commands; the standard set is:
What ships with it
1 file 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.
- 2mo ago First seen · 136 lines · 28 tokens per session scan A 1f232ef34ca8
package-upgrade is a skill published in the GitHub repository john-data-chen/hermes-agent-backup (2 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 1,604 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
pipeline-conductor
Operating procedure for the kirocrew-pipeline-conductor agent. Use when a pipeline conductor session is seeded, inspected or debugged. You MANAGE one issue/PR pipeline on one repo: two columns per item (session working? item solved?), send intent, never re-derive a red yourself.
commit
Skill "commit" from clacky-ai/openclacky, covering smart commit skill, critical requirement: single-line commits only, core philosophy, usage and process steps.
release-notes
Draft a release note section from a commit range, grouped by what the reader gets.
fork-fleet
Fork divergence monitor - tracks where the fleet's active forks diverge in CODE (unique commits, new/modified skills) and CONFIG (enable/var/model/schedule vs upstream), gated on real change.
aeon-update
Pull framework updates from the upstream Aeon repo into this instance - 3-way merges canon's new commits into a PR, never clobbering operator config.