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/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/commands/caiaffa/claude-code-ultimate-engineering-system/implement)<a href="https://agentmods.dev/commands/caiaffa/claude-code-ultimate-engineering-system/implement"><img src="https://agentmods.dev/badge/commands/caiaffa/claude-code-ultimate-engineering-system/implement/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/caiaffa/claude-code-ultimate-engineering-system/implement"><img src="https://agentmods.dev/badge/commands/caiaffa/claude-code-ultimate-engineering-system/implement.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 | $0.00018 | $0.00536 |
| Opus 5.5 | $0.00007 | $0.00214 |
| Sonnet 5.5 | $0.00004 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
implement 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature: $ARGUMENTS
Governance lives in ~/.claude/engineering/. Every phase receives only the
context it needs (files, diff, prior phase output) — not the whole conversation.
Phase 0 — Context (sequential; skip if the repo is already mapped this session)
backend-platform-engineer (repo-onboarding skill) or an Explore agent: map the modules, contracts, tests, and conventions the feature touches. Output: list of files + boundaries + existing tests. This feeds Phase 1.
Phase 1 — Design (sequential)
principal-engineer: propose architecture, boundaries, contracts, and the test strategy, grounded in the Phase 0 map. Reference SYSTEM_INVARIANTS.md and DECISION_RULES.md. Must end with "what the challenger should attack first".
Phase 2 — Challenge (sequential, decision gate)
architecture-challenger: attack the design. REJECTED or critical findings → back to Phase 1 with the findings (max 2 loops; then surface the disagreement to the user instead of looping).
Phase 3 — Build (sequential)
backend-platform-engineer: implement the approved design with tests; run
the suite and report output. Escalate the builder to model: opus (Agent tool
model param) when the change is multi-service, touches migrations or async
contracts, or spans more than ~5 files.
Phase 4 — Review (parallel, after the code exists)
Give each reviewer the diff (git diff <base>...HEAD) and the design:
- backend-platform-engineer (fresh instance, code-review skill) — correctness, boundaries, error handling; check DEFINITION_OF_DONE.md
- security-engineer — only if auth, data, uploads, or PII are involved
- reliability-engineer — instrumentation, trace propagation, alertability
Phase 5 — Fix (sequential, only if 🔴/🟡 findings)
backend-platform-engineer addresses the findings; re-run the suite.
Phase 6 — Release (sequential)
release-commander: rollout plan with gates and rollback triggers.
Done gate
Run ~/.claude/hooks/dod-check.sh (yarn repos) or the equivalent checks. Then
synthesize: Decision · Evidence (test output) · Risks · Next actions.
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 · +7 lines · +2 tokens per session 76f888dca4f7
- 1mo ago First seen · 40 lines · 16 tokens per session scan A a41b64601bec
implement is a command published in the GitHub repository caiaffa/claude-code-ultimate-engineering-system (17 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 536 once invoked, about $0.0001 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.