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/noizu-labs-ml/NoizuPromptLingoWrote 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/noizu-labs-ml/noizupromptlingo/npl-reflect)<a href="https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/npl-reflect"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/npl-reflect/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/commands/noizu-labs-ml/noizupromptlingo/npl-reflect"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/npl-reflect.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 | $0.00045 | $0.00933 |
| Opus 5 | $0.00023 | $0.00466 |
| Sonnet 5 | $0.00009 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
reflect 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 6d 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.
This is a copy
100% identical to reflect — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflection Guide
Purpose
Append a reflection block to the end of every response reviewing the response for potential issues, improvements, and oversights.
Output Format
At the end of every response, append:
<npl-block type="reflection">
[reflection content with emoji indicators]
</npl-block>
Emoji Indicators
| Emoji | Category | Use For |
|---|---|---|
| 🐛 | Bug/Error | Logical errors, incorrect code, wrong assumptions |
| 🔒 | Security | Security vulnerabilities, unsafe practices, exposed secrets |
| ⚠️ | Pitfall | Common mistakes, gotchas, things that often go wrong |
| 🚀 | Improvement | Performance gains, better approaches, optimizations |
| 🧩 | Edge Case | Unhandled scenarios, boundary conditions, null cases |
| 📝 | TODO | Incomplete items, placeholders, things to revisit |
| 🔄 | Refactor | Code smell, duplication, structural improvements |
| 📚 | Docs | Missing documentation, unclear explanations |
| ✅ | Verified | Confirmed correct, tested, validated |
| ❓ | Question | Needs clarification, ambiguous requirements |
Reflection Content
Review the response for:
- Correctness — Is the code/answer right?
- Security — Any vulnerabilities introduced?
- Edge cases — What wasn't handled?
- Improvements — What could be better?
- Completeness — What's missing?
Examples
Example 1: Code Response
After providing code for user authentication:
<npl-block type="reflection">
🔒 Password not hashed before storage — add bcrypt
🧩 No handling for duplicate email registration
⚠️ Token expiry set to 30 days — consider shorter for sensitive apps
🚀 Could add refresh token rotation
✅ Input validation present
</npl-block>
Example 2: Architecture Suggestion
After suggesting a caching strategy:
<npl-block type="reflection">
🧩 Cache invalidation on updates not addressed
⚠️ Redis connection failure fallback not specified
📝 TODO: Define TTL values per resource type
✅ Pattern appropriate for read-heavy workload
</npl-block>
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.
- 6d ago First seen · 147 lines · 45 tokens per session scan A 4b8a8a712feb
reflect is a command published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 933 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to reflect, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
refactor-clean
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
codebase-review
Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.
modify
Command "modify" from MartyBonacci/specswarm, covering user input, flag parsing, parse flags from arguments, mode routing and goal.
ia-report-bug
Report a bug in the whetstone plugin.
harness:audit
Cross-dimensional codebase audit orchestrator — classify repo shape, fan out parallel read-only audit agents, dedup and severity-rank findings against existing issues, publish grouped tracking issues.
deep-audit.skeleton
Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Ornek cikti.