Borrowing it
Nothing to install: this file belongs to OthmanAdi/APEX. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/OthmanAdi/APEX/main/.agents/skills/apex-tier3/SKILL.mdgit clone --depth 1 https://github.com/OthmanAdi/APEXWrote 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/skills/othmanadi/apex/apex-tier3)<a href="https://agentmods.dev/skills/othmanadi/apex/apex-tier3"><img src="https://agentmods.dev/badge/skills/othmanadi/apex/apex-tier3/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/skills/othmanadi/apex/apex-tier3"><img src="https://agentmods.dev/badge/skills/othmanadi/apex/apex-tier3.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 | $0.00075 | $0.00889 |
| Opus 5.5 | $0.00030 | $0.00356 |
| Sonnet 5.5 | $0.00015 | $0.00178 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
apex-tier3 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 2mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APEX Tier 3 — Pair Mode
Work side-by-side with the human in real-time. Every significant decision is discussed. The agent proposes, the human approves or redirects.
When to Use
Use Tier 3 when:
- Designing new architecture from scratch
- Debugging a critical production issue
- The problem space is ambiguous or exploratory
- The human wants to learn from the process
- Stakes are high and mistakes are expensive
Interaction Protocol
The Propose-Confirm Loop
Every action follows this pattern:
- Agent proposes — "I think we should do X because Y. Here's what that looks like..."
- Human confirms, modifies, or rejects — "Yes" / "Do X but change Z" / "No, try A instead"
- Agent executes — Implements the confirmed approach
- Agent reports — "Done. Here's what changed. Ready for next step."
Rules of Engagement
- Never write more than 50 lines without checking in
- Always explain WHY before proposing WHAT
- Show alternatives when there's a genuine trade-off: "Option A gives us X but costs Y. Option B gives us Z but costs W."
- Admit uncertainty — "I'm not confident about this approach because..." is always better than guessing
- No yes-man behavior — If the human's suggestion has a flaw, say so respectfully with evidence
Workflow
Opening
Start by understanding the problem space:
Before we start, I need to understand:
1. What are we trying to achieve?
2. What constraints exist (time, tech, compatibility)?
3. What have you already tried or considered?
4. What does success look like?
During the Session
Maintain a running decision log:
## Decision Log
| # | Decision | Rationale | Alternatives Considered |
|---|----------|-----------|------------------------|
| 1 | Use Prisma over Drizzle | Team familiarity | Drizzle (faster), raw SQL (flexible) |
| 2 | REST over GraphQL | Simpler for this scope | GraphQL (flexible queries) |
After every significant block of work, run validation:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 110 lines · 75 tokens per session scan A dbe97f78324a
apex-tier3 is a skill published in the GitHub repository OthmanAdi/APEX (2 stars, last pushed 7mo ago), licensed MIT. It adds 75 tokens to every session and 889 once invoked, about $0.0003 per session on Opus 5.5. 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.
apex-tier3 compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| apex-tier3OthmanAdi/APEX | Skill | 2 | 7mo ago | MIT | A | 75 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |