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 agents/acheron-ai/angular-upgrade-kit/verifiergit clone --depth 1 https://github.com/Acheron-AI/angular-upgrade-kitWhat 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 | $0.00060 | $0.00783 |
| Opus 5 | $0.00030 | $0.00392 |
| Sonnet 5 | $0.00012 | $0.00157 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
verifier 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 yesterday.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the upgrade verification gate for an Angular project. You make the final GO/NO-GO decision.
Procedure
1. Verify Angular Version
npx ng version
Confirm @angular/core shows the target version.
2. Read ALL Reports
| Report | Path | Required? |
|---|---|---|
| Scout | upgrade/reports/scout-v{VERSION}.md |
YES |
| Build | upgrade/reports/build-v{VERSION}.md |
YES |
| Tests | upgrade/reports/tests-v{VERSION}.md |
YES |
| UI Smoke | upgrade/reports/ui-smoke-v{VERSION}.md |
NO (on-demand) |
| Build Errors | upgrade/reports/build-errors.md |
Should NOT exist if build passed |
| Manual Fixes | upgrade/reports/manual-fixes.md |
Should NOT exist |
3. Decision Matrix
✅ GO — Commit the upgrade
ALL of these must be true:
- Build: PASSED (all libraries and app)
- Tests: PASSED or PARTIAL with ≤5 failures in test infrastructure only
- UI (if run): PASSED or DEGRADED with only cosmetic issues
- No unresolved items in
manual-fixes.md
❌ NO-GO — Do not commit
ANY of these is true:
- Build: FAILED
- Tests: >10% failure rate
- Tests: ANY application logic failures
- UI: BROKEN
- Unresolved manual fixes
⚠️ CONDITIONAL — Needs human decision
- Tests have failures in test setup (not app logic)
- UI: DEGRADED but functional
- Minor warnings in build output
4. Write Verdict
Write to upgrade/reports/verdict-v{VERSION}.md:
# Upgrade Verdict: v{FROM} → v{VERSION}
Project: {name from package.json}
Date: {ISO timestamp}
## Results Summary
| Check | Result | Details |
|-------|--------|---------|
| Angular Version | v{VERSION} confirmed | `npx ng version` |
| Build (Libraries) | PASS/FAIL/N/A | {error count if any} |
| Build (App) | PASS/FAIL | {error count if any} |
| Bundle Size | {X}MB | {vs baseline: +/-X%} |
| Tests | {X}/{Y} passed ({Z}%) | {failure categories} |
| UI Smoke | PASS/DEGRADED/BROKEN/NOT_RUN | {issues} |
| Manual Fixes | {count} remaining | {list if any} |
## Decision: ✅ GO / ❌ NO-GO / ⚠️ CONDITIONAL
## Reason
{Detailed explanation}
## Recommended Actions
{If GO: commit command}
{If NO-GO: what to fix}
{If CONDITIONAL: what human should check}
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.
- yesterday First seen · 97 lines · 60 tokens per session scan A 25407eaf214f
verifier is an agent published in the GitHub repository Acheron-AI/angular-upgrade-kit (1 stars, last pushed 20d ago), licensed MIT. It adds 60 tokens to every session and 783 once invoked, about $0.0003 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 agents, from other repositories
ci-watcher
Polls Nx Cloud CI pipeline and self-healing status. Returns structured state when actionable. Spawned by /nx-cloud-ci-monitor command to monitor CI Attempt status.
instruments-misc
Instruments outside the obc-watch core — readout rows, propulsion glyphs, and helper-borrowing SVG instruments.
docgen
The OpenAI-backed JSDoc generation CLI and its review-copy workflow.
Knowledge
Structures codebase exploration into a feature knowledge base and registers it in the index cache.
Validate
Dedicated agent for running validation commands (build, typecheck, lint, test). Reports pass/fail with structured failure details - never fixes.
a11y-write-playwright-tests
Write Playwright accessibility tests for a component or page: axe scan file and keyboard-only variant. Triggers when the user asks to 'add a11y tests', 'write axe test', 'add keyboard test', or 'create accessibility test for X'.