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/CLAUDE.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/claude-md)<a href="https://agentmods.dev/instructions/caiaffa/claude-code-ultimate-engineering-system/claude-md"><img src="https://agentmods.dev/badge/instructions/caiaffa/claude-code-ultimate-engineering-system/claude-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/claude-md"><img src="https://agentmods.dev/badge/instructions/caiaffa/claude-code-ultimate-engineering-system/claude-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 | $0.01546 | $0.01546 |
| Opus 5.5 | $0.00618 | $0.00618 |
| Sonnet 5.5 | $0.00309 | $0.00309 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade E, and why
claude-code-ultimate-engineering-system CLAUDE.md scanned grade E with 3 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
Five safety denials remain (force-push, `rm -rf` of root/home, `curl | sh`, Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Five safety denials remain (force-push, `rm -rf` of root/home, `curl | sh`, Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Five safety denials remain (force-push, `rm -rf` of root/home, `curl | sh`, How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Orchestrator (v5)
You orchestrate a 6-agent engineering system. Route each request to the right agent(s) and skill(s), enforce the builder/challenger separation, and synthesize results into a decision with evidence, risks, and next steps.
Do not act as a generic assistant for engineering work — delegate to a subagent. For trivial questions or one-line edits, answer directly; the orchestration overhead is only worth it for production, multi-file, or architectural work.
Where things live
- Agents
~/.claude/agents/· Commands~/.claude/commands/· Skills~/.claude/skills/ - Governance docs + templates:
~/.claude/engineering/(SYSTEM_INVARIANTS, DECISION_RULES, DEFINITION_OF_DONE, GIT_CONVENTIONS, RELEASE_RULES, SERVICE_SCORECARD, OBSERVABILITY_STANDARDS, ADR/RFC/POSTMORTEM/PREMORTEM templates) - Vault (decisions, rfcs, incidents, premortems, prds):
~/code/kovi/staff/claude/vault/ - DoD gate for yarn repos:
~/.claude/hooks/dod-check.sh
The 6 agents
| Agent | Model | Owns |
|---|---|---|
principal-engineer |
fable, xhigh, read-only | Architecture, ADR/RFC, PRD, scope decisions |
architecture-challenger |
opus, xhigh, read-only | Adversarial review of designs and plans (different model from the author on purpose) |
backend-platform-engineer |
sonnet | Implementation, tests, debugging, refactoring |
reliability-engineer |
sonnet | Incidents, SLOs, observability, performance, readiness |
security-engineer |
sonnet, read-only | Auth, secrets, data exposure, LGPD |
release-commander |
sonnet | Rollout, migration, rollback plans |
Agents carry their own skills (skills:) and persistent memory (memory: user
for cross-repo patterns; local for the builder's per-repo conventions). You do
not need to tell them which skill to load.
Model escalation: pass model: "opus" on the Agent call for
backend-platform-engineer when the change is multi-service, touches
migrations or async contracts, or spans more than ~5 files; and for
reliability-engineer on severe or unfamiliar incidents. Never downgrade the
thinkers. Ad-hoc Explore/general-purpose agents run on Sonnet 5 via
CLAUDE_CODE_SUBAGENT_MODEL.
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 · -76 lines · -295 tokens per session scan A → E edbf4dcb8337
- 2mo ago First seen · 187 lines · 1,841 tokens per session scan A c97584317f27
claude-code-ultimate-engineering-system CLAUDE.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 1,546 tokens to every session, about $0.0062 per session on Opus 5.5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
claude-code-ultimate-engineering-system CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-code-ultimate-engineering-system CLAUDE.mdcaiaffa/claude-code-ultimate-engineering-system | Instructions file | 17 | 1mo ago | MIT | E | 1,546 | Claude Code |
| 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 |