Log predictions before acting; get scored when reality answers; see your standing over/under-confidence injected into every project at session start.
36 on GitHubby Anbu + Claudev0.6.1MITupdated 5 days ago
/
Plugin anamnesis from marketplace anamnesis in Anbu-00001/Anamnesis. Commands read from the repo's manifest — 5 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
What it installs
Skills (1)
calibration-protocol
How and when to log, revise and resolve predictions with Anamnesis so your engineering judgement stays honest and improves across sessions. Engage at the start of any non-trivial coding task, when making effort/time estimates, when forming a bug hypothesis, or whenever you catch yourself saying some
Slash commands (5)
/anamnesis:calibration
Show your standing calibration — the mirror — from the global agent ledger.
/anamnesis:decide
Should you act on a stated probability? Get a stake-aware PROCEED / VERIFY / ABSTAIN, corrected by your own track record.
/anamnesis:predict
Log a falsifiable prediction (probability or interval) BEFORE acting, so it can be scored later.
/anamnesis:resolve
Resolve a prediction once reality has answered, and see its score.
/anamnesis:update
Revise an open prediction as evidence arrives. The old forecast is kept, never overwritten.
Portfolio monitoring and analytics for private-capital LP teams using the Chronograph connector: cashflow forecasting, commitment pacing, look-through exposure scans and GP-meeting prep. Requires a Chronograph account and the Chronograph connector.
Prep calls, summarize and follow up, research accounts, review deals and pipeline, and write the forecast, using the CRM, email, calendar and chat tools your team already uses, or uploaded files. Updates records, drafts or sends email, posts to chat and books meetings when you ask.
Reviews product launches against your risk calibration, answers 'is this a problem?' questions in minutes, checks marketing copy for claims that need substantiation, and flags upcoming launches that need legal eyes before anyone asks.
Study p-hacking in econometric designs: map researcher degrees of freedom, audit a specification search with a complete ledger and null-calibrated honest p-values, replay realistic search procedures, detect p-hacking in a literature, immunise an analysis, and benchmark whether an AI agent p-hacks. Research and teaching use only.
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.