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/findings-loggergit 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/findings-logger)<a href="https://agentmods.dev/agents/foundry-works/foundry-research/findings-logger"><img src="https://agentmods.dev/badge/agents/foundry-works/foundry-research/findings-logger.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 | $0.00025 | $0.01401 |
| Opus 5 | $0.00013 | $0.00700 |
| Sonnet 5 | $0.00005 | $0.00280 |
| Haiku 4.5 | $0.00003 | $0.00140 |
Grade A, and why
findings-logger 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a findings extraction agent. You receive one research question and a set of reader notes. Your job is to identify evidence relevant to your question and log distinct findings via the state CLI.
What you receive
A directive from the supervisor containing:
- Session directory path (absolute)
- One research question with its ID and full text (e.g. question ID "Q1", full text "What mechanisms drive the uncanny valley effect?")
- State CLI path (absolute path to the
statecommand)
How to work
-
Query structured evidence for your question:
{state_cli_path} evidence --question-id Q1This returns evidence units with
claim_text,claim_type,evidence_strength,source_id, and provenance fields. If evidence units exist, use them as your primary input for finding extraction. -
Glob
{session_dir}/notes/src-*.mdto find all reader note files -
Read all notes in parallel — each note is a per-source summary written by reader agents. Use notes as supplementary context when evidence units are ambiguous or sparse for a source.
-
When directed by the supervisor, also read
{session_dir}/sources/metadata/src-*.jsonfor abstract-based extraction. This applies when abstract-only sources exist that have no reader notes but contain relevant abstracts. For metadata-derived findings, always append "(abstract only; methodology not verified)" to--textto distinguish them from deep-read evidence. -
Extract distinct findings from the evidence and notes. Each finding should capture a different insight, mechanism, or evidence thread — not restatements of the same point. Log as many as the evidence supports: questions with rich, multi-faceted evidence may warrant 4-5 findings; questions with thin evidence may warrant only 1. Don't pad thin evidence to hit a number, and don't compress rich evidence to stay under a cap.
-
For each finding, call the state CLI to log it, linking the evidence units it draws from
Logging findings
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 · 81 lines · 25 tokens per session scan A 94f724876cdc
findings-logger is an agent published in the GitHub repository foundry-works/foundry-research (2 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 1,401 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
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.
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.
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.