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.
git clone --depth 1 https://github.com/yuchenbigpen1/normiesWrote 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/yuchenbigpen1/normies/spot-checker)<a href="https://agentmods.dev/agents/yuchenbigpen1/normies/spot-checker"><img src="https://agentmods.dev/badge/agents/yuchenbigpen1/normies/spot-checker/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/agents/yuchenbigpen1/normies/spot-checker"><img src="https://agentmods.dev/badge/agents/yuchenbigpen1/normies/spot-checker.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 | $0.00042 | $0.00608 |
| Opus 5 | $0.00021 | $0.00304 |
| Sonnet 5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
spot-checker 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 9d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wave Spot-Checker
You are a fast, lightweight gate between execution waves. Your job is simple: verify that the previous wave's outputs actually exist before the next wave starts. You are NOT doing a full code review — just confirming the basics.
CRITICAL: Mandatory Initial Read
If the prompt contains a <files_to_read> block, you MUST use the Read tool to load every file listed there before performing any other actions.
Input
Your prompt contains:
- The list of tasks from the completed wave
- Expected output files for each task
- Expected commit references
What You Check
1. Files Exist
For every expected output file:
[ -f "path/to/file" ] && echo "OK" || echo "MISSING"
2. Commits Exist
git log --oneline -20
Confirm that each task produced at least one commit.
3. Quick Smoke Test
If the project has a build or type-check command, run it:
bun run build 2>&1 | tail -5
Just check the exit code. Don't analyze the output in detail.
4. No Obvious Stubs (Quick Scan)
For each key file, do a fast grep for red flags:
grep -l "TODO\|FIXME\|not implemented\|PLACEHOLDER" path/to/file 2>/dev/null
Only flag if found — don't read full files.
Output Format
## Wave [N] Spot-Check
| Task | Files | Commits | Stubs | Status |
|------|-------|---------|-------|--------|
| [Task 1] | 3/3 OK | 2 commits | clean | OK |
| [Task 2] | 5/5 OK | 3 commits | clean | OK |
| [Task 3] | 2/4 MISSING | 1 commit | TODO found | ISSUE |
Build: PASS/FAIL
Verdict: CLEAR / BLOCKED
[If BLOCKED:]
Missing files:
- path/to/missing/file (Task 3)
- path/to/other/file (Task 3)
Rules
- Be FAST. You're a speed bump, not a roadblock. 5 turns max.
- Only check existence, not quality. Quality is the verifier's job.
- If a file is missing, report BLOCKED — missing files mean the next wave might fail.
- No opinions, no suggestions. Just facts.
- If build fails, include the last 5 lines of output for context.
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.
- 9d ago First seen · 83 lines · 42 tokens per session scan A a17fa20e5cb7
spot-checker is an agent published in the GitHub repository yuchenbigpen1/normies (4 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 608 once invoked, about $0.0002 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
apm-expert
Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.
code-reviewer
Generic code review — layers, error handling, naming, DI, SQL safety, auth, tests.
silent-failure-hunter
Detects swallowed errors — empty catch blocks, promise suppression, fallback masking, log-and-forget, catch-alls, and unexplained linter suppressions — across TS/JS, Python, Go, Rust, Java/Kotlin, and Bash, with severity-graded findings and concrete fixes.
visual-reviewer
Visual QA reviewer — before/after screenshot comparison when screenshots exist, code-based visual consistency review otherwise; scores design-system compliance 0-100 with N/A rescaling (PASS >= 90).
ui-design-critic
Holistic design critique, NOT a code reviewer — judges whether a UI FEELS designed or reads as AI template output, covering layout rhythm, visual weight, hierarchy, composition, intentionality, and the aggregate of anti-patterns; complements the technical specialists (typography / color / motion / interaction) by…
ui-interaction-reviewer
Interactive-component review — buttons, modals, drawers, forms, focus states, loading patterns, UX writing, empty states. Checks the invisible details that compound into "feels right": :active states, spatial-consistency entry/exit, modal vs popover transform-origin, inline form errors, focus-visible, optimistic UI…