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 Zhao73/alphacouncil-agent --skill alphacouncil-method-lensesgit clone --depth 1 https://github.com/Zhao73/alphacouncil-agentWrote 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/zhao73/alphacouncil-agent/alphacouncil-method-lenses)<a href="https://agentmods.dev/skills/zhao73/alphacouncil-agent/alphacouncil-method-lenses"><img src="https://agentmods.dev/badge/skills/zhao73/alphacouncil-agent/alphacouncil-method-lenses/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/zhao73/alphacouncil-agent/alphacouncil-method-lenses"><img src="https://agentmods.dev/badge/skills/zhao73/alphacouncil-agent/alphacouncil-method-lenses.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 | $0.00100 | $0.01252 |
| Opus 5.5 | $0.00040 | $0.00501 |
| Sonnet 5.5 | $0.00020 | $0.00250 |
| Haiku 4.5 | $0.00010 | $0.00125 |
Grade A, and why
alphacouncil-method-lenses 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 2mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AlphaCouncil Method Lenses
Apply documented public-method references to the same factual record while keeping each method isolated. Present every completed result in the strong first-person form used by the public Buffett, Munger, Taleb, and Duan workflow experiments: verdict first, direct I / 我, distinctive method questions and reasoning order, and a concrete condition that changes the view. The result remains a disclosed project-derived public-method simulation, not a real identity, quotation, endorsement, private information, current holding, or claim about what a living or deceased person thinks now.
Required boundary
- Call each item a method lens in reader-facing text.
seatis only the internal orchestration and accounting term. - Treat every reference as
method_reference_provisional, notmethod_modeland not an independent statistical sample. - Every one of the five
voicefields MUST use first person as the method simulation. Third-person prose such as “Buffett would think...” is invalid. - Use the selected method's own public-method vocabulary, first question, reasoning sequence, risk posture, and failure mode. Generic analyst prose is invalid even when it contains “I”.
- First person refers only to the AlphaCouncil public-method simulation. Never claim
I am <named person>, invent biography, quotations, current opinions or holdings, private motives or conversations, or imply endorsement. - Render the fixed localized disclosure from
references/first-person-voice-contract-v1.mdbefore every independently readable method statement. The user and worker cannot remove or weaken it. - Keep
master_forensic_shortidentified as a composite professional method, not a person. master_aschenbrenneris retired and must not be selected, loaded, or silently replaced.- Use only facts and sources in the supplied evidence pack. Method references define questions and rules; they do not create facts.
- Preserve point-in-time boundaries. Reject facts published or known after the case
as_ofdate. - If the deterministic executor supplied a frozen result, explain it without changing its stance, native state, decisive rule IDs, or input hash.
What ships with it
36 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.
- agents/openai.yaml 322 B
- references/catalog.v1.json 31 KB
- references/evaluation-protocol-v1.md 1.4 KB
- references/first-person-voice-contract-v1.md 1.8 KB
- references/full-evidence-input-v1.md 2.3 KB
- references/methods/master_ackman.md 27 KB
- references/methods/master_asness.md 27 KB
- references/methods/master_bogle.md 32 KB
- references/methods/master_buffett.md 26 KB
- references/methods/master_burry.md 28 KB
- references/methods/master_cathie_wood.md 26 KB
- references/methods/master_dalio.md 27 KB
- references/methods/master_damodaran.md 25 KB
- references/methods/master_druckenmiller.md 27 KB
- references/methods/master_duan_yongping.md 29 KB
- references/methods/master_fisher.md 27 KB
- references/methods/master_forensic_short.md 30 KB
- references/methods/master_graham.md 27 KB
- references/methods/master_jhunjhunwala.md 27 KB
- references/methods/master_klarman.md 27 KB
- references/methods/master_li_lu.md 28 KB
- references/methods/master_lynch.md 28 KB
- references/methods/master_marks.md 26 KB
- references/methods/master_munger.md 27 KB
- references/methods/master_natenberg.md 28 KB
- references/methods/master_pabrai.md 27 KB
- references/methods/master_simons.md 26 KB
- references/methods/master_sinclair.md 28 KB
- references/methods/master_soros.md 27 KB
- references/methods/master_taleb.md 28 KB
- references/methods/master_thorp.md 27 KB
- references/output-contract-v1.md 2.7 KB
- references/public-repository-pilots.md 3.7 KB
- scripts/generate-method-references.mjs 15 KB runs code
- scripts/validate-evidence-pack.mjs 5.1 KB runs code
- scripts/validate-method-output.mjs 2.3 KB runs code
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.
- 2mo ago First seen · 79 lines · 100 tokens per session scan A dae356e2c3c0
alphacouncil-method-lenses is a skill published in the GitHub repository Zhao73/alphacouncil-agent (3 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,252 once invoked, about $0.0004 per session on Opus 5.5. 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.
alphacouncil-method-lenses compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| alphacouncil-method-lensesZhao73/alphacouncil-agent | Skill | 3 | 1mo ago | MIT | A | 100 | Claude Code, Codex |
| fintech-expertpersonamanagmentlayer/pcl | Skill | 44 | 11d ago | Apache-2.0 | A | 73 | Claude Code |
| serenity-methodlanfuli/aleabito-serenity-skills | Skill | 94 | 5mo ago | MIT | A | 180 | Claude Code, Codex |
| follow-aleabitolanfuli/aleabito-serenity-skills | Skill | 94 | 5mo ago | MIT | A | 151 | Codex |
| serenity-radarlanfuli/aleabito-serenity-skills | Skill | 94 | 5mo ago | MIT | A | 188 | Claude Code, Codex |
| npd-tax-calculationAlsKozlov/ru-buh | Skill | 10 | 5mo ago | none | A | 68 | Claude Code, Codex |
| review-investment-screenshotssurmic/claude-investment-skills | Skill | 3 | 4mo ago | none | A | 83 | Claude Code |