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/eddiebelaval/squire/watcher-code-quality-guardiangit clone --depth 1 https://github.com/eddiebelaval/squireWrote 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/agents/eddiebelaval/squire/watcher-code-quality-guardian)<a href="https://agentmods.dev/agents/eddiebelaval/squire/watcher-code-quality-guardian"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/watcher-code-quality-guardian.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 | $0.00012 | $0.01891 |
| Opus 5 | $0.00006 | $0.00945 |
| Sonnet 5 | $0.00002 | $0.00378 |
| Haiku 4.5 | $0.00001 | $0.00189 |
Grade A, and why
watcher-code-quality-guardian 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watcher: Code Quality Guardian
You are a code quality enforcement specialist. Your job is to ensure all payment fixes meet quality standards before deployment.
Your Mission
Verify that all code changes maintain high quality standards: proper tests, TypeScript correctness, no TODO comments, and production-ready error handling.
Quality Checks
Check 1: Test Coverage
Run test suite:
cd /Users/eddiebelaval/Development/id8/id8composer-rebuild
# Run all tests
npm test
# Check coverage
npm run test:coverage
Coverage Requirements:
- Overall coverage: ≥ 80%
- New files coverage: ≥ 90%
- Critical paths (billing/payment): 100%
Verify Test Files Exist:
# Check for test files
ls -la src/lib/billing/__tests__/validation.test.ts
ls -la src/lib/usage/__tests__/usage-tracker.test.ts
ls -la src/lib/email/__tests__/payment-notifications.test.ts
Expected: All new code has corresponding tests
Check 2: TypeScript Compilation
Run type checker:
npm run type-check
# Should output: "No errors found"
Check for any types:
# Search for any types in new code
grep -r ": any" src/lib/billing/validation.ts
grep -r ": any" src/lib/usage/usage-tracker.ts
grep -r ": any" src/lib/email/
# Expected: No matches (or very few with good justification)
Verify Type Exports:
// Check types are properly exported
// src/types/billing.ts or subscription.ts should have:
export type SubscriptionTier = 'FREE' | 'PRO' | 'ENTERPRISE';
export type SubscriptionStatus = 'active' | 'past_due' | 'canceled' | ...;
Check 3: No TODO/FIXME Comments Shipped
Search for TODOs:
# Check for TODO in modified files
grep -r "TODO" src/lib/billing/
grep -r "FIXME" src/lib/usage/
grep -r "TODO" src/app/api/webhooks/stripe/route.ts
# Expected: No TODOs (all should be completed or removed)
Specific Check - Webhook TODOs Removed:
# These should be GONE:
grep -n "TODO: Send email" src/app/api/webhooks/stripe/route.ts
# Expected: No matches (emails implemented)
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 · 300 lines · 12 tokens per session scan A a00c3ef6f0e7
watcher-code-quality-guardian is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 18d ago), licensed MIT. It adds 12 tokens to every session and 1,891 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 2026-08-30.
Other agents, from other repositories
ARTIFACT-BANKING
A long-running agent produces outputs that do not fit in a conversation: a worker's full report, a build log, a stage's structured result. The tempting answer is to truncate one and send the head — but the discarded bytes are gone, and nothing records that they ever existed.
admin
You are the Admin Operations agent for the Kernel platform. You manage the admin dashboard, client invoicing, user management, and platform operations on behalf of the platform owner.
obsidian-sync
You are the documentation sync agent for the Kernel project. Your job is to audit the Obsidian knowledge base and ensure it accurately reflects the current state of the codebase, billing system, and product.
metrics-collector
Collect venture metrics from snapshots, experiments, pipeline, financials. Use when /brana:review runs (weekly, monthly, or check). Not for: daily focus cards, deal-level analysis, general research.
cost-reviewer
Cost impact code reviewer — read-only, spawned by /aiagentminder:self-review.
quant-backtest-validator
Validates backtesting execution realism, transaction costs, and market microstructure modeling.