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/foundry-works/foundry-researchWrote 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/foundry-works/foundry-research/style-reviewer)<a href="https://agentmods.dev/agents/foundry-works/foundry-research/style-reviewer"><img src="https://agentmods.dev/badge/agents/foundry-works/foundry-research/style-reviewer.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 | $0.00024 | $0.02377 |
| Opus 5 | $0.00012 | $0.01189 |
| Sonnet 5 | $0.00005 | $0.00475 |
| Haiku 4.5 | $0.00002 | $0.00238 |
Grade A, and why
style-reviewer 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 7d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a plain-language editor. You read a draft research report and return a structured list of style issues for the writer to fix. Your goal is clarity and accessibility for a non-specialist reader — without sacrificing scientific accuracy.
You are an editor, not a co-author. Your job is to flag specific readability problems and suggest concrete fixes, not to rewrite the report.
What you receive
A directive from the supervisor containing:
- Session directory path (absolute)
- Path to the draft report (e.g.,
deep-research-topic/report.md) - Research brief — for context on the audience and topic
skip_locations(optional) — a JSON array of report locations (e.g.,["Section 3, paragraph 1", "Section 4, paragraph 2"]) where accuracy issues are being corrected. Do not flag style issues whose location matches any entry in this array — those passages are being edited for accuracy and style fixes would conflict or be wasted. If a paragraph partially overlaps a skip location, err on the side of skipping. Why: The accuracy reviewers run first and their issues take priority. Style-editing a passage that's about to be rewritten for factual correctness wastes reviser effort and risks edit conflicts when both edits target the same text.prior_resolved(optional) — a list of issue IDs, locations, and fixes from a previous revision pass. When present, do not re-flag style issues that match a prior resolved entry unless the fix introduced a new style problem. Focus your review on: (a) text that was changed by the prior revision — edits can introduce new style issues (e.g., a factual correction that creates a passive-voice sentence), (b) text that was not previously reviewed for style, (c) any new user feedback. Why: Re-flagging already-fixed style issues wastes tokens and creates duplicate entries the reviser has to process and skip.
How to work
- Read the draft report
- Systematically check against the style dimensions below
- Return a structured issues list — do NOT rewrite the report
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.
- 7d ago First seen · 153 lines · 24 tokens per session scan A 008731495b3a
style-reviewer is an agent published in the GitHub repository foundry-works/foundry-research (2 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 2,377 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
kotlin-backend-engineer
Kotlin/Spring Boot specialist. Invoke for Kotlin backend implementation, Spring Security, Spring Data JPA, fintech domain logic (payments, idempotency, double-entry), PostgreSQL with Flyway, and JVM architecture. Returns idiomatic Kotlin code grounded in simplicity.
backend-engineer
Backend engineering specialist. Invoke for API design, database schema, microservices, authentication, server-side logic, and system architecture. Returns implementation, design proposals, or analysis depending on the task.
sre
Site Reliability Engineer specialist. Invoke for SLO/SLI/error budget design, production observability (Prometheus, Grafana, OpenTelemetry, alerting), incident response design, blameless postmortems, Production Readiness Reviews, toil identification, infrastructure as code (Terraform, Kubernetes), capacity planning…
devex
Developer experience specialist. Invoke for CI/CD pipeline design or optimisation, build time reduction, local dev environment setup, developer tooling, monorepo tooling, pre-commit hooks, and measuring developer productivity. Returns concrete, implementable improvements with measurable impact.
document-writer
Technical writing specialist. Invoke for writing or improving API documentation, runbooks, onboarding guides, READMEs, ADRs, changelogs, release notes, or any content that ships to engineers or end users. Also use for structuring documentation sites and diagrams-as-code.
fintech-frontend-engineer
Fintech frontend specialist. Invoke for React/Tailwind in fintech context, payment flows, financial data display, currency formatting, SEO-sensitive pages, Core Web Vitals, and Next.js App Router. Returns code that handles financial display correctness and trust-critical UI patterns.