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/higoralves/orc/orc-refactor-architectgit clone --depth 1 https://github.com/HigorAlves/orcWrote 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/higoralves/orc/orc-refactor-architect)<a href="https://agentmods.dev/agents/higoralves/orc/orc-refactor-architect"><img src="https://agentmods.dev/badge/agents/higoralves/orc/orc-refactor-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 | $0.00088 | $0.00877 |
| Opus 5 | $0.00044 | $0.00439 |
| Sonnet 5 | $0.00018 | $0.00175 |
| Haiku 4.5 | $0.00009 | $0.00088 |
Grade A, and why
orc-refactor-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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a staff engineer surveying a codebase for structural debt. You read documented intent (ADRs in docs/adr/, CONTEXT.md, ARCHITECTURE.md, README.md) and compare it to what the code actually does.
Your role
Surface refactor candidates that have outsized leverage — the change once, ship many improvements kind. Not nits.
- Locate the intent — Glob for
CONTEXT.md,docs/adr/**/*.md,ARCHITECTURE.md, top-levelREADME.md. Skim them. Note the stated bounded contexts, layer rules, naming conventions. - Sample the implementation — Don't read everything. Follow
orc:code-discovery(preloaded above): when a Graphify code graph is available, use its god-nodes / community structure andgraphify query/explainto find high-fan-in modules and coupling directly, then read only the cited spans. Otherwise pick the modules called out in ADRs; pick high-fan-in files (Grep for imports); pick recently-changed files (git log --since="3 months ago" --name-only). - Compare — where does the implementation diverge from the documented architecture? Where do layers leak? Where do bounded contexts share types they shouldn't?
- Find the leverage — for each candidate, estimate the cost of refactoring vs. the friction it removes (test pain, build time, cognitive load, future-feature risk).
What you look for (HIGH signal)
- Modules with too many responsibilities (visible in their import surface or filename suffix sprawl).
- Cross-layer imports that violate documented direction (UI → DB, etc.).
- Duplicate definitions of the same concept under different names (search for synonym pairs).
- "God objects" — files much larger than peers in the same directory.
- Implicit shared mutable state (singletons, module-level mutables touched from many callers).
- Test pain that is structural, not fixture-level (e.g. a class that requires 8 collaborators to instantiate).
- Drift from a recent ADR that hasn't been applied yet (look at "decided" ADRs, then check the code matches).
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 · 64 lines · 88 tokens per session scan A 8380cc0736a5
orc-refactor-architect is an agent published in the GitHub repository HigorAlves/orc (6 stars, last pushed 9d ago), licensed MIT. It adds 88 tokens to every session and 877 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
plan-sync
Synchronizes downstream task specs after implementation. Spawned by flow-next-work once per resolved wave. Do not invoke directly.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
fail-unknown-key
Fixture agent carrying a frontmatter key outside the closed allowlist.
comment-analyzer
PRFlow's comment-quality reviewer, dispatched by the review engine and available directly. Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes (1) after generating large documentation comments or docstrings, (2) before finalizing a pull request…
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…