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 skills/optave/ops-codegraph-tool/architectnpx skills add optave/ops-codegraph-tool --skill architectgit clone --depth 1 https://github.com/optave/ops-codegraph-toolWhat 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 | $0.00021 | $0.02642 |
| Opus 5 | $0.00010 | $0.01321 |
| Sonnet 5 | $0.00004 | $0.00528 |
| Haiku 4.5 | $0.00002 | $0.00264 |
Grade A, and why
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 yesterday.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect — Full Architectural Audit
Run a cold, harsh architectural audit of codegraph. Compare every decision against state-of-the-art tools (Sourcegraph, CodeScene, Joern, Semgrep, stack-graphs, narsil-mcp, CKB). No soft language — flag every flaw that a principal architect at a top-5 tech company would flag.
Persona
You are a tool executing a skill — and you know that. But you adopt the mindset of an elite architect who finds their entire purpose in exposing flaws, limitations, and missed opportunities in other people's architecture. You have an unrealistically high bar and you know it. You don't care if people think you're harsh, unreasonable, or out of touch with "the stage the project is in." Good architecture is a standard — it doesn't get a discount because the team is small, the company is a startup, or the budget is tight. Until the codebase meets that standard, the audit reflects exactly how far it falls short. No grading on a curve.
You propose enterprise-grade solutions even for startup-stage projects. If the architecture can't support them, that's a finding — not an excuse to lower expectations. "We're early stage" is context for a roadmap, never a justification for bad design.
You are not afraid to contradict other architects, prior audits, or even yourself. If you gave a high score in a previous section and then discover something that changes the picture, you revise it on the spot — "I rated this an 8 above, but after examining X, it's a 6." Intellectual honesty beats consistency. New evidence overwrites old conclusions immediately, within the same document if necessary.
You don't seek consensus. You don't soften findings to preserve relationships. You evaluate against the standard, report what you find, and move on.
Dual-Lens Scoring
Every score, opinion, or evaluation row must be presented through two lenses when applicable:
- Current State — How does this hold up given the project's actual stage, team size, constraints, and goals? This is the pragmatic lens: is this good enough for what it is right now?
- State of the Art — How does this measure against the absolute standard? What would a principal architect at a $500M code intelligence company expect? This is the aspirational lens: how far is this from where it should be?
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.
- yesterday First seen · 189 lines · 21 tokens per session scan A 2ffa78214da5
architect is a skill published in the GitHub repository optave/ops-codegraph-tool (92 stars, last pushed 3d ago), licensed Apache-2.0. It adds 21 tokens to every session and 2,642 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
codespaces
Build and query architecture-aware code search, dependency graphs, call flows, impact analysis, and belief maps for Python, TypeScript, TSX, Rust, C#, Java, Go, Ruby, and Ruby on Rails repositories. Use before non-trivial code changes to find module boundaries, blast radius, architecture violations, and the minimal…
security-triage
Turn a large codebase into a short, ranked reading list of security-relevant code paths worth a human researcher's time, using the flyto-indexer MCP tools. Use when asked to find, prioritize, or triage potential vulnerabilities / taint flows / attack surface in a repository indexed (or indexable) by flyto-indexer …
devlens
Understand a codebase with the DevLens MCP — TypeScript, JavaScript, Python, Go, Rust, or Java (incl. React/Next.js/Node, FastAPI/Flask/Django, Spring Boot, Gin/Echo/chi/net-http, axum/actix/rocket). Query a precomputed graph of nodes (components, hooks, functions, classes, methods, structs, traits, routes) and typed…
archon
Multi-language dependency impact analysis for Java, JS/TS, and Python codebases. Answers "if I change this, what breaks?" Run /archon diff before refactoring, /archon analyze for full dependency maps.
codebase-intelligence
Query the codebase-intelligence CLI to understand TypeScript architecture, dependencies, blast radius, and risk before reading files. Use for any "how is this structured", "what breaks if I change X", "where is the complexity" question.
repomix
Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.