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 skills add iFurySt/aifi --skill research-evidence-archivegit clone --depth 1 https://github.com/iFurySt/aifiWrote 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/skills/ifuryst/aifi/research-evidence-archive)<a href="https://agentmods.dev/skills/ifuryst/aifi/research-evidence-archive"><img src="https://agentmods.dev/badge/skills/ifuryst/aifi/research-evidence-archive/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ifuryst/aifi/research-evidence-archive"><img src="https://agentmods.dev/badge/skills/ifuryst/aifi/research-evidence-archive.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.00478 |
| Opus 5 | $0.00030 | $0.00239 |
| Sonnet 5 | $0.00012 | $0.00096 |
| Haiku 4.5 | $0.00006 | $0.00048 |
Grade A, and why
research-evidence-archive 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 12d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Evidence Archive
Use this skill whenever research materials need to be saved, reused, or linked across AIFi workflows. The archive is part of the product: old material should compound into better future research instead of disappearing into chat history.
Workflow
- Identify the
ResearchTargetand archive path. - Create the target directory if it does not exist.
- Save source material in the right subdirectory.
- Record metadata, retrieval date, source URL or file origin, and confidence.
- Deduplicate against existing material before adding new files.
- Link synthesized notes back to raw evidence.
- Update indexes so future skills can discover reusable material quickly.
Archive Layout
Use this default layout:
research/
targets/
<ticker-or-slug>/
profile.md
index.md
evidence/
filings/
earnings/
news/
market/
competitors/
risks/
media/
artifacts/
memos/
decision-frames/
watchlists/
Read references/archive-layout.md before creating or reorganizing archive
files.
Evidence Rules
- Prefer markdown for extracted notes and structured summaries.
- Preserve original files when they are useful: PDFs, images, spreadsheets, HTML snapshots, and downloaded datasets can live beside markdown summaries.
- Never overwrite useful prior evidence without preserving history or explaining why it is obsolete.
- Every synthesized claim should link to one or more evidence items.
- Label generated analysis separately from source material.
Output
Return:
- files created or updated
- sources stored
- duplicates skipped
- stale or missing metadata
- next skills that can consume the archive
Quality Gate
Before finishing, check:
- target archive has an
index.md - new evidence has source and retrieval metadata
- raw and synthesized materials are clearly separated
- paths are stable and lowercase where practical
- no secrets, paid-content dumps, or private account data were stored
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 78 lines · 61 tokens per session scan A a29e22754f26
research-evidence-archive is a skill published in the GitHub repository iFurySt/aifi (22 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 478 once invoked, about $0.0003 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 skills, from other repositories
daily-deep-brief
A scheduled, pre-market investment briefing for Hong Kong and United States stocks. A deterministic preparation step gathers data and an agent adds judgment, while a later step validates and publishes the result.
hk-stock-analysis
A workspace-aware analysis workflow for Hong Kong-listed stocks. It retrieves prices, technical indicators, market comparisons, and news through a local data pipeline, then adds Hong Kong-specific investment context.
us-stock-analysis
Workspace-aware US stock analysis for kcn. Routes through clawock analyze-us / clawock us-quotes instead of generic web search, then layers fundamental/technical/news analysis on top. Use when user asks to analyze a US ticker (e.g. "analyze AAPL", "look at RKLB", "compare TSLA vs NVDA"), check earnings, run…
portfolio-swarm-review
Multi-agent swarm review of kcn's current holdings. Inspired by TauricResearch/TradingAgents framework already in workspace — three-tier analysis (analysts → bull/bear debate → risk debate + judge) with confidence scoring. Use for post-close reviews, holiday/next-session planning, pre-add sizing decisions, and any…
investment-decision
Run a clawock investment decision — read the prepared request, research with the host's own tools, write decision.json with evidence and an explicit bull/bear debate, and let Python validate and settle. Use when the user asks for an investment decision or a clawock run request is present.
portfolio-risk-review
Single-pass holdings analysis for kcn using workspace files and the local fetch chain. Use for portfolio review, position risk ranking, US-HK cross-market read, leverage ETF risk assessment, and one-shot actionable reports based on portfolio.json plus fresh quotes from clawock analyze-us / clawock analyze-hk.