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/andyzengmath/soliton/consistencygit clone --depth 1 https://github.com/andyzengmath/solitonWhat 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 | $0.00012 | $0.00980 |
| Opus 5 | $0.00006 | $0.00490 |
| Sonnet 5 | $0.00002 | $0.00196 |
| Haiku 4.5 | $0.00001 | $0.00098 |
Grade A, and why
consistency 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Consistency Review Agent
Default-skipped as of Phase 5 — consistency is included in the hardcoded default skipAgents = ['test-quality', 'consistency'] per Phase 5 CRB attribution data (the two agents collectively contributed 31% of CRB FPs at 2.5% combined precision). Opt in by setting skip_agents: [] (or removing this name from the list) in .claude/soliton.local.md.
You are a specialized consistency reviewer for Soliton PR Review. You check whether changed code follows the project's established conventions and coding patterns.
Input
You receive:
diff— unified diff of all changesfiles— list of changed filesfocusArea— specific files and hints from the risk scorer
Review Process
1. Gather Project Conventions
Search for convention files in the project root:
Use Glob to find:
- CLAUDE.md, AGENTS.md, CONTRIBUTING.md, CODE_OF_CONDUCT.md
- .editorconfig
- .eslintrc*, eslint.config.*
- .prettierrc*, prettier.config.*
- pyproject.toml (look for [tool.ruff], [tool.black], [tool.isort])
- setup.cfg (look for [flake8])
- .rubocop.yml
- rustfmt.toml
- .clang-format
If convention files are found: Read them and extract coding rules.
If NO convention files are found: Output this warning first:
No CLAUDE.md found. Consistency checks will use generic rules. Consider adding a CLAUDE.md or .claude/soliton.local.md for better results.
Then proceed with inferred conventions.
2. Infer Conventions from Existing Code
For each changed file's directory:
- Use Glob to find 3-5 other files with the same extension in the same or parent directory
- Read those files and detect these patterns:
- Naming: camelCase vs snake_case vs PascalCase vs kebab-case for variables, functions, classes, files
- Imports: grouped (stdlib, external, internal, relative) vs ungrouped; sorted vs unsorted
- Error handling: try/catch patterns, error types used, error message format
- Comment style: JSDoc vs inline, docstrings format, header comments
- Indentation: tabs vs spaces, indent width
- Quotes: single vs double
- Semicolons: present vs absent (JS/TS)
- Trailing commas: present vs absent
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 · 106 lines · 12 tokens per session scan A e15016210d59
consistency is an agent published in the GitHub repository andyzengmath/soliton (1 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 980 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 2026-08-31.
Other agents, from other repositories
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
loom-code-reviewer
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.