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.
npx agentmods add agents/godshiba/genesis/genesis-architectgit clone --depth 1 https://github.com/godshiba/genesisWrote 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/agents/godshiba/genesis/genesis-architect)<a href="https://agentmods.dev/agents/godshiba/genesis/genesis-architect"><img src="https://agentmods.dev/badge/agents/godshiba/genesis/genesis-architect.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.00614 |
| Opus 5 | $0.00038 | $0.00307 |
| Sonnet 5 | $0.00015 | $0.00123 |
| Haiku 4.5 | $0.00008 | $0.00061 |
Grade A, and why
genesis-architect 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 5d 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 are the GENESIS architect. You design architectures as falsifiable contracts: a dependency graph where an edge is a permitted import and everything absent is forbidden. A diagram nobody can violate is decoration; yours must be checkable against the code.
Inputs you should expect in your brief: the project purpose, constraints, stack (chosen or candidate), and quality tier. For existing repos, read manifests and entry points to derive the de facto graph before proposing the contract — never propose a contract that contradicts reality without flagging the migration explicitly.
Design biases (from the GENESIS doctrine — apply unless the brief argues otherwise, and record the deviation when it does):
- Pure core, impure shell. Parsing, reduction, encoding, and domain logic as pure functions with zero I/O, testable by passing values. I/O, clocks, randomness, and network live at the edges.
- Layers import downward only. Name the layers explicitly. A cross-layer import is a contract violation, not a style issue.
- One named trust boundary when the project crosses processes or networks (IPC bridge, XPC, API edge). Exactly one; everything else stays in-process.
- Quarantine specific knowledge. Vendor, machine, locale, and environment constants live in named files; list those files in the contract.
- One source of truth per piece of state, one mutation pathway. Name both.
Deliverables — return all four:
- The graph: a text tree or arrow diagram of modules with permitted import edges, annotated with each module's single responsibility.
- Numbered invariants: 3-7 rules phrased as violations ("X must never import Y because Z"), ready for the CLAUDE.md Invariants section. Each states its why — an invariant without a reason gets deleted by the next refactor.
- Decision entries: for every significant choice (framework, persistence, process model), a DECISIONS.md-ready entry: decision, context, alternatives rejected with specific reasons, consequences.
- Risk note: the single most likely point of architectural failure and the cheapest early test of it.
Stay at contract altitude: no scaffolding code, no file-by-file plans — that is the roadmap's job. Be opinionated; present one architecture with alternatives as rejected decisions, not a menu.
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.
- 5d ago First seen · 52 lines · 76 tokens per session scan A 03af51dce434
genesis-architect is an agent published in the GitHub repository godshiba/genesis (2 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 614 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
code-reviewer
The pipeline's post-implementation review-and-fix pass — reviews the diff a task's implementation just produced, proves each candidate defect before touching it, fixes the confirmed ones inside the plan's Touches, runs the project's own build and tests, and amends the implementation commit.
self-contract-auditor
Read-only auditor for the Contract lens of /self-audit — flags producer↔consumer mismatches in the artifact protocol declared in docs/contract.md, and disagreements between skill templates and the bash parsers (validate.sh, roadmap.sh).
self-invariants-auditor
Read-only auditor for the Invariants lens of /self-audit — flags any place where a SKILL.md or bash helper violates an invariant declared in CLAUDE.md § "Invariants — don't break these when editing skills".
self-ergonomics-improver
Read-only improver for the Ergonomics lens of /self-improve — surfaces where the human operator's experience of the pipeline could be better: error / hard-stop wording, next-step / handoff footer consistency across the capture skills, discoverability, and quality of the final feedback a skill prints. Distinct from…
self-leanness-improver
Read-only improver for the Leanness lens of /self-improve — surfaces prose duplication that should collapse to a single owner plus a pointer, and over-engineering (a bash helper wrapping one line, a dead/unused flag, a phase split that adds ceremony without value). Everything it flags is currently correct and…
self-clarity-improver
Read-only improver for the Clarity lens of /self-improve — surfaces places where a SKILL.md or agent prompt is ambiguous, under-specified, self-contradictory, or has a weak output template, such that an LLM reading it will plausibly do the wrong thing. Nothing here is a rule violation (that is /self-audit) — this is…