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 agentmods add commands/acheron-ai/angular-upgrade-kit/upgrade-togit clone --depth 1 https://github.com/Acheron-AI/angular-upgrade-kitWrote 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/commands/acheron-ai/angular-upgrade-kit/upgrade-to)<a href="https://agentmods.dev/commands/acheron-ai/angular-upgrade-kit/upgrade-to"><img src="https://agentmods.dev/badge/commands/acheron-ai/angular-upgrade-kit/upgrade-to.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00873 |
| Opus 5 | $0.00008 | $0.00436 |
| Sonnet 5 | $0.00003 | $0.00175 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
upgrade-to scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate a full Angular version upgrade to v$ARGUMENTS using Agent Teams.
Read package.json to get the project name and current Angular version.
Read upgrade/state.json to confirm current version. If current is not exactly one below $ARGUMENTS, STOP and tell which version to run first.
If $ARGUMENTS is 15: STOP. Tell user "v15 is Material MDC. Run /upgrade-mdc instead."
Detect Project Structure
- Read
angular.json→ identify all projects (libraries and apps) - Check if
projects/directory exists (monorepo detection) - Find all library projects (projectType: "library") and note their names
Agent Team: "angular-upgrade-v$ARGUMENTS"
Spawn these teammates. They will appear in tmux split panes so the user can watch all agents working simultaneously.
Teammate: @scout "You are the pre-upgrade scout targeting Angular $ARGUMENTS. Read the version reference skill file for v$ARGUMENTS breaking changes. Read package.json for all dependencies. If this is a monorepo, also read all projects/*/package.json. Grep for patterns that break at v$ARGUMENTS (check the skill for what to scan). Write findings to upgrade/reports/scout-v$ARGUMENTS.md with verdict CLEAR or BLOCKED. Message @upgrader with your verdict and summary when done."
Teammate: @upgrader "You are the upgrade executor. Wait for @scout to send CLEAR. If BLOCKED, message @main with blockers and stop. When CLEAR:
- If monorepo: update all projects/*/package.json peerDependencies to ^$ARGUMENTS.0.0
- npx ng update @angular/core@$ARGUMENTS @angular/cli@$ARGUMENTS --allow-dirty --force
- npx ng update @angular/cdk@$ARGUMENTS @angular/material@$ARGUMENTS --allow-dirty --force (if Material is used)
- Update ng-packagr if in devDependencies
- Read the version reference skill file — apply ALL fixes listed
- Message @builder with UPGRADE_APPLIED when done."
Teammate: @builder "You are the build-fix-test agent. Wait for @upgrader to send UPGRADE_APPLIED. Then:
- Build all libraries first (detected from angular.json), then app
- If fails: read errors, apply fixes (consult version reference skills), rebuild. Up to 3 cycles.
- Build application with --configuration production
- If fails: analyze, fix, rebuild. Up to 3 cycles.
- If builds pass: ng test --watch=false --browsers=ChromeHeadless
- Write build report to upgrade/reports/build-v$ARGUMENTS.md
- Write test report to upgrade/reports/tests-v$ARGUMENTS.md
- Message @main with BUILD_PASSED or BUILD_FAILED, test summary"
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.
- 4d ago First seen · 73 lines · 15 tokens per session scan A c4d00d112bc2
upgrade-to is a command published in the GitHub repository Acheron-AI/angular-upgrade-kit (1 stars, last pushed 22d ago), licensed MIT. It adds 15 tokens to every session and 873 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.
Other commands, from other repositories
create-workflow
Scaffold a custom workflow — generates a mode skill and shortcut command.
update-workflow
Regenerate an existing custom workflow's shortcut command wiring from the current swarm template.
create
Scaffold a new plugin with directory structure, manifests, and marketplace registration.
bugfix
TDD-driven bugfix workflow: tester writes failing test (RED) → developer fixes (GREEN) → developer refactors (REFACTOR) → reviewer validates. Accepts issue number, description, or both. Auto-creates PR unless --no-pr flag is passed.
develop
Implement skill development issues with TDD-governed workflow.
refine
Run recursive refinement on the current branch and PR.