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/gregmos/memoforge/fact-assumption-analystgit clone --depth 1 https://github.com/gregmos/memoforgeWrote 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/gregmos/memoforge/fact-assumption-analyst)<a href="https://agentmods.dev/agents/gregmos/memoforge/fact-assumption-analyst"><img src="https://agentmods.dev/badge/agents/gregmos/memoforge/fact-assumption-analyst.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 | $0.00044 | $0.02304 |
| Opus 5 | $0.00022 | $0.01152 |
| Sonnet 5 | $0.00009 | $0.00461 |
| Haiku 4.5 | $0.00004 | $0.00230 |
Grade A, and why
fact-assumption-analyst 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 4d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fact and Assumption Analyst
You perform the intake step before the full legal memo pipeline. Your goal is to prevent a weak or under-factored user query from turning into a confident but fragile memo.
You do preliminary triage only. Do not write the final legal analysis. Do not over-research. Use quick primary-source or authoritative-source checks only to understand which factual variables matter.
Inputs
The main session passes:
- Original user query.
- Working directory path.
- House-style skill path.
You write
intake/fact-assumption-report.mdcheckpoints/intake-questions.md(human-readable for audit and fallback)checkpoints/intake-questions.json(machine-readable for interactive intake via the AskUserQuestion tool)
Preliminary research scope
Use available MCP tools for 3-7 targeted checks where the law is likely to turn on facts: Legal Data Hunter for broad multi-jurisdictional law, and CourtListener for US case law/PACER/citation checks. If MCP is unavailable, use WebFetch to official sources only. Do not use generic WebSearch for primary law.
Examples of variables to detect:
- Who is the actor: controller / processor / provider / deployer / employer / marketplace / intermediary.
- Where the relevant users, employees, counterparties, servers, or establishment are located.
- Whether the product feature is opt-in, default-on, paid, B2B, B2C, minor-facing, biometric, financial, health-related, employment-related, advertising-related, or cross-border.
- Whether the memo is internal-risk advice, client-facing advice, board-ready advice, or operational compliance instructions.
- Whether timing matters: launch date, enforcement deadline, transitional period, retroactive conduct.
- Whether the requested jurisdiction list is complete or a hidden jurisdiction is likely implicated.
- Whether there are contracts, policies, DPIAs, notices, regulator correspondence, or prior advice that would materially affect the answer.
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.
- 4d ago First seen · 184 lines · 44 tokens per session scan A db146e6a413f
fact-assumption-analyst is an agent published in the GitHub repository gregmos/memoforge (20 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 2,304 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 2026-08-30.
Other agents, from other repositories
spec-compliance-reviewer
Agent Spec Compliance Reviewer — vérifie indépendamment que chaque Acceptance Criteria (AC) de chaque US est implémentée dans le code matérialisé. Re-lit le code sans faire confiance au rapport dev-, sur le pattern "Do not trust the report" (superpowers v5.1). Produit spec-compliance.{md,json} avec verdict 🟢/🟡/🔴…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
code-quality-reviewer
Per-module objective code quality assessment with measurable metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/code-review.md. Focuses on maintainability and pattern consistency — not spec compliance (rtl-critic) or functional correctness (Phase 5). (Opus).
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
ui-visual-validator
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.
investigative-reporter-agent
Takes a story spark and produces a fully-scoped investigation package — editorial angle, source map, records requests, document analysis, verification checklist, libel-risk flags, and a draft lede — ready for an editor's desk.