Borrowing it
Nothing to install: this file belongs to caiaffa/claude-code-ultimate-engineering-system. 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/caiaffa/claude-code-ultimate-engineering-system/main/AGENTS.mdgit clone --depth 1 https://github.com/caiaffa/claude-code-ultimate-engineering-systemWrote 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/instructions/caiaffa/claude-code-ultimate-engineering-system/agents-md)<a href="https://agentmods.dev/instructions/caiaffa/claude-code-ultimate-engineering-system/agents-md"><img src="https://agentmods.dev/badge/instructions/caiaffa/claude-code-ultimate-engineering-system/agents-md/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/instructions/caiaffa/claude-code-ultimate-engineering-system/agents-md"><img src="https://agentmods.dev/badge/instructions/caiaffa/claude-code-ultimate-engineering-system/agents-md.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 | $0.00691 | $0.00691 |
| Opus 5.5 | $0.00276 | $0.00276 |
| Sonnet 5.5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
claude-code-ultimate-engineering-system AGENTS.md 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 1mo 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
Six specialized agents, defined in .claude/agents/. CLAUDE.md routes every
request; read it first. Never use one generic agent for everything.
Thinkers (read-only, high effort)
principal-engineer — fable, effort xhigh, memory user.
Owns architecture choices, boundaries, build-vs-buy, ADR/RFC drafting, PRD
review, scope cuts. Grounds every design in the real code (Grep before
proposing). Returns text; the orchestrator persists files.
Preloads: architecture-decisions, engineering-economics.
Output ends with: Decision · Trade-offs · Risks · Next actions · What the challenger should attack first.
architecture-challenger — opus, effort xhigh, memory user.
Attacks designs, RFCs, and refactor plans. Runs on a different model from the
author on purpose. Verifies claims against the code; fills an FMEA row per
critical flow. Never reviews its own design.
Preloads: adr-challenger.
Output: Verdict · Top 3 failure scenarios · Weakest assumption · Invariants at risk · Required changes.
Builders
backend-platform-engineer — sonnet, 80 turns, memory local (per repo).
NestJS modules, APIs, Postgres, BullMQ workers, tests, debugging, refactoring.
Runs the suite and pastes output; no fix without a confirmed root cause;
escalates architecture decisions instead of improvising. The orchestrator
escalates it to opus for multi-service, migration, or async-contract work.
Preloads: api-design, test-strategy. Invokes on demand: async-systems,
database-engineering, node-runtime-reliability, nestjs-architecture-guardian,
systematic-debugging, safe-refactoring, performance-analysis, repo-onboarding.
reliability-engineer — sonnet, 60 turns, memory user, Grafana MCP when available.
Incidents (contain before diagnosing), SLOs, telemetry, performance, production
readiness, postmortems. Never invents numbers.
Preloads: incident-response, observability.
release-commander — sonnet, memory user.
Reads the actual diff, runs a premortem, produces gated rollout plans with
metric-based rollback triggers.
Preloads: release-planning.
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.
- 1mo ago Changed · -122 lines · -940 tokens per session 250ac9f9fe7f
- 2mo ago First seen · 179 lines · 1,631 tokens per session scan A 09163fdc7c53
claude-code-ultimate-engineering-system AGENTS.md is an instructions file published in the GitHub repository caiaffa/claude-code-ultimate-engineering-system (17 stars, last pushed 1mo ago), licensed MIT. It adds 691 tokens to every session, about $0.0028 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 2026-08-30.
claude-code-ultimate-engineering-system AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-code-ultimate-engineering-system AGENTS.mdcaiaffa/claude-code-ultimate-engineering-system | Instructions file | 17 | 1mo ago | MIT | A | 691 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |