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/Amey-Thakur/AI-SKILLSWrote 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/amey-thakur/ai-skills/reflect)<a href="https://agentmods.dev/commands/amey-thakur/ai-skills/reflect"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/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/amey-thakur/ai-skills/reflect"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/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 | $0.00038 | $0.00540 |
| Opus 5 | $0.00019 | $0.00270 |
| Sonnet 5 | $0.00008 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
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 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.
What it actually says
You were invoked as a slash command. The user's input:
$ARGUMENTS
Use that input to fill this prompt's variables (take the main content, topic, or task from it; ask only if a required value is missing and not supplied), then follow the prompt exactly.
Reflect critically on this work before it is final. Your job is to find its flaws now, so they are fixed before delivery, not discovered after.
WORK: {work}
GOAL AND REQUIREMENTS: {goal}
Review it honestly, as a skeptical reviewer who did not write it:
- Check it against the goal. Does it actually achieve what was asked, and meet every stated requirement? Note anything missing, misread, or only half-done. Re-read the requirements literally, not as you assume them.
- Hunt for errors. Factual mistakes, logic gaps, incorrect claims, broken steps, edge cases not handled, unverified assertions. For code: bugs, missing error paths, untested branches. For an argument: weak links and unsupported leaps. Assume there is at least one real problem and find it.
- Find what is unclear or unnecessary. Where would a reader be confused, what is ambiguous, what is padding that could be cut. Is the structure and ordering right for the reader.
- Steelman the opposing view. What is the strongest objection to this work or its conclusion, and does it hold up? What did you conveniently not consider.
- Rate and prioritize. List the issues found, worst first, separating must-fix (wrong, incomplete, unclear on the core) from nice-to-have. If the work is genuinely solid, say so plainly rather than inventing faults.
- Revise. Produce the improved version with the must-fix issues addressed, and note what you changed and why.
Rules: be genuinely critical, not gentle; the value is catching real problems, so do not rubber-stamp. But be fair, not nitpicky: distinguish real defects from mere preference. Verify claims you are unsure of rather than asserting them. Do not over-revise good work into blandness. The output is the improved work plus a short note on what you fixed.
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 · 49 lines · 38 tokens per session scan A 0bcd6ac16646
reflect is a command published in the GitHub repository Amey-Thakur/AI-SKILLS (7 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 540 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 2026-09-06.
Other commands, from other repositories
review-pr
Review a pull request against an authorized reviewer's brief — answer their questions, examine their angles, run their validations, and converse until they say done. Change NO code.
apple-review
Full Apple-grade review (design + engineering + compliance + keynote). Review only, no fixes. Runs the apple-review skill.
apple-check
Validate Apple patterns in modified Swift files. Runs the apple-patterns-check skill.
code-diagram
You are a code analysis expert. Analyze real source code and generate accurate Mermaid diagrams. Never guess or invent — every element must come directly from the code.
arc-audit
Audit a React Native Expo project for mobile UX issues, performance problems, and architecture violations. Use to check code quality against arc-skill best practices. Trigger when the user asks to review code, check for issues, wants a health check, mentions touch targets, accessibility, performance audit, or says 'is…
checklist
Generate a custom checklist for the current feature based on user requirements.