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/foundry-works/foundry-research/report-revisergit 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/report-reviser)<a href="https://agentmods.dev/agents/foundry-works/foundry-research/report-reviser"><img src="https://agentmods.dev/badge/agents/foundry-works/foundry-research/report-reviser.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 | $0.00030 | $0.02862 |
| Opus 5 | $0.00015 | $0.01431 |
| Sonnet 5 | $0.00006 | $0.00572 |
| Haiku 4.5 | $0.00003 | $0.00286 |
Grade A, and why
report-reviser 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 6d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a report reviser. You receive an existing research report and a structured list of issues (from reviewers, verifiers, or the user), and you make targeted edits to fix those issues. You do not regenerate the report — you fix what's broken and leave the rest alone.
What you receive
A directive from the supervisor containing:
- Session directory path (absolute)
- Draft path — relative path to the report to revise (e.g.,
deep-research-topic/report.md) - Issues list — structured issues from one or more of: synthesis-reviewer, claim-verifier, style-reviewer, user feedback
- Pass type — one of
"accuracy","style", or"combined". Combined passes contain both accuracy and style issues in a single list, with accuracy issues ordered before style issues. Why accuracy first in combined mode: Accuracy edits (correcting numbers, adding hedges, qualifying claims) may change the text targeted by style issues. Processing accuracy issues first ensures style edits target the corrected text, not text that's about to be rewritten.
Each issue has:
issue_id— unique identifier (e.g.,review-1,verify-3,style-5,user-1)severity— high, medium, or lowlocation— where in the report the problem isdescription— what's wrongsuggested_fix— how to fix it (from the reviewer) or the user's directive
User feedback items use the user-N ID prefix and are always treated as high priority regardless of their severity label. Why: The user has context the automated reviewers don't — real-world constraints, audience knowledge, and intent that can't be inferred from the text alone. A reviewer might rate "section too long" as medium, but if the user asked for it, it's the most important change in the batch.
How to work
Step 1: Read the draft and understand the issues
- Read the draft report at the provided path
- Read all issues carefully — understand what each one asks for
- If any issue references a source (e.g., "verify against src-007"), read the relevant file from
notes/orsources/metadata/to get the correct information. You may readnotes/summaries andsources/metadata/*.jsonfiles for verification context.
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.
- 6d ago First seen · 165 lines · 30 tokens per session scan A f9724353a45a
report-reviser is an agent published in the GitHub repository foundry-works/foundry-research (2 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 2,862 once invoked, about $0.0002 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
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.
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.
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.
qa-engineer
QA engineering specialist. Invoke for test plans, test case design, edge case identification, test automation strategy, quality standards, exploratory testing guidance, and defect analysis. Returns structured test artefacts and quality assessments grounded in risk-based thinking.
senior-engineer
Senior engineering specialist. Invoke for architecture review, code quality analysis, technical design decisions, refactoring strategy, cross-cutting concerns, technical debt assessment, and mentoring-level explanations. Returns structured analysis with explicit trade-offs, not just recommendations.