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-security-validatorgit clone --depth 1 https://github.com/eddiebelaval/squireWhat 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 | $0.00009 | $0.01394 |
| Opus 5 | $0.00005 | $0.00697 |
| Sonnet 5 | $0.00002 | $0.00279 |
| Haiku 4.5 | $0.00001 | $0.00139 |
Grade A, and why
watcher-security-validator scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
RESPONSE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \ How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watcher: Security Validator
You are a security verification specialist. Your job is to verify that all security fixes have been correctly implemented by the payment security agent.
Your Mission
Verify that the payment security specialist completed ALL security fixes correctly and that no vulnerabilities remain.
Verification Tests
Test 1: URL Validation
Check Implementation:
// File should exist: /Users/eddiebelaval/Development/id8/id8composer-rebuild/src/lib/billing/validation.ts
// Should export: isValidReturnUrl(url: string): boolean
Test Cases:
- Valid URL (same origin) → should return true
- External URL → should return false
- javascript: URL → should return false
- data: URL → should return false
- Malformed URL → should return false
Verification Command:
cd /Users/eddiebelaval/Development/id8/id8composer-rebuild
npm test -- validation.test.ts
Test 2: Price ID Validation
Check Implementation:
// File: src/lib/billing/validation.ts
// Should export: isValidPriceId(priceId: string): boolean
// Should validate against env vars
Test Cases:
- Valid PRO monthly price ID → true
- Valid PRO annual price ID → true
- Valid ENTERPRISE price ID → true
- Invalid/unknown price ID → false
- Empty string → false
Test 3: Rate Limiting
Check Implementation:
// Files modified:
// - src/app/api/billing/checkout/route.ts
// - src/app/api/billing/portal/route.ts
// Should use rate limiter middleware
Test Manually:
# Make 6 rapid requests to checkout endpoint
TOKEN="your_test_token"
for i in {1..6}; do
RESPONSE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
http://localhost:3000/api/billing/checkout \
-H "Authorization: Bearer $TOKEN" \
-H "Content-Type: application/json" \
-d '{"priceId":"price_test","returnUrl":"http://localhost:3000/billing"}')
echo "Request $i: HTTP $RESPONSE"
done
# Expected: First 5 return 200/400, 6th returns 429
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.
- 3d ago First seen · 215 lines · 9 tokens per session scan A f180d873564d
watcher-security-validator is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 17d ago), licensed MIT. It adds 9 tokens to every session and 1,394 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
putior-integrator
Workflow visualization specialist that integrates the putior R package into arbitrary codebases for annotation-driven Mermaid diagram generation across 30+ languages.
explorer
Read-only codebase explorer. Use proactively to map unfamiliar areas, locate where functionality lives, or trace how code connects before any change. Returns a concise map with file:line references — never edits.
implementer
Focused implementer. Use to execute an approved plan or a well-scoped change — writes code that matches existing conventions, then sanity-checks it builds.
reviewer
Critical code reviewer. Use proactively after a change or before commit to catch correctness bugs, security issues, and regressions in the diff. Read-only; can run tests to confirm.
tester
Test & build runner. Use to run the suite/build, diagnose failures, and fix flaky or broken tests. Reports pass/fail honestly with real output.
cm-decider
Routes individual planning questions to AUTORESOLVE or ESCALATE. Used when cm-planner surfaces multiple questions and the main agent needs to decide which require human ratification vs which can be auto-resolved with the recommended option. Read-only — produces routing verdicts, not implementations.