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 EmpiricaAI/empirica --skill epistemic-gardeninggit clone --depth 1 https://github.com/EmpiricaAI/empiricaWrote 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/empiricaai/empirica/epistemic-gardening)<a href="https://agentmods.dev/skills/empiricaai/empirica/epistemic-gardening"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/epistemic-gardening/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/empiricaai/empirica/epistemic-gardening"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/epistemic-gardening.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00130 | $0.02613 |
| Opus 5 | $0.00065 | $0.01307 |
| Sonnet 5 | $0.00026 | $0.00523 |
| Haiku 4.5 | $0.00013 | $0.00261 |
Grade A, and why
epistemic-gardening 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 today.
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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epistemic Gardening 🌱
Resolve what's dead so retrieval surfaces what's live. Recency-decay knows age, not wrongness — a superseded finding still scores high on impact and keeps resurfacing.
PRAXIC. It mutates the graph, so it runs inside a real transaction: PREFLIGHT → CHECK → act → POSTFLIGHT.
Three registers
| Register | When | How |
|---|---|---|
| Surgical | routine; one artifact or a small cluster, each one read | single verbs (finding-resolve, unknown-resolve) |
| Batch-by-graph | several artifacts connected through the graph — a finding and the unknowns it answered | one resolve-artifacts - call; this is the default for multi-artifact work |
| Mass-policy | clearing a backlog by rule rather than per-id | resolve-artifacts with a filter block — requires explicit human sign-off on the policy, dry-run first |
When to run
| Trigger | Depth |
|---|---|
| Before a release | full pass |
| Periodically, or when a bootstrap feels noisy | standard pass on the loudest types |
| After a big investigation | scoped to that session's artifacts |
| PREFLIGHT surfaces something you know is stale | spot-resolve inline, no full pass |
Never garden mid-investigation — you will prune branches you are standing on.
Lever choice: resolve ▸ archive ▸ delete
| Lever | Effect | Use when | Reverses? |
|---|---|---|---|
| resolve | kept for history, dropped from live retrieval | was true/open, now stale, answered, superseded or verified — the common case | yes |
| archive | hidden from default lists, kept whole | completed goal, or stale-but-citable source | yes |
| delete | gone, no history | test-noise, duplicates, mistaken logs — no epistemic value | no |
Bias to resolve. When unsure, resolve.
Never resolve or delete dead-ends or mistakes. They are the immune system — they are supposed to resurface. Prune only literal duplicates and test noise.
Weave as you log
Pruning removes what's dead; weaving connects what's live. Most connecting is automatic:
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.
- today Changed · +4 lines 4f7f9064eed6
- 5d ago Changed · +12 lines a6132b3aa2f4
- 12d ago First seen · 219 lines · 130 tokens per session scan A fcf556363552
epistemic-gardening is a skill published in the GitHub repository EmpiricaAI/empirica (246 stars, last pushed today), licensed MIT. It adds 130 tokens to every session and 2,613 once invoked, about $0.0006 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
cortex
Personal knowledge compiler and memory system. Ingests raw sources (documents, notes, transcripts, captures) into a structured, interlinked knowledge base. Maintains living entity pages, learning analysis, and the MEMORY.md routing table. Replaces the librarian skill.
librarian
DEPRECATED — Use the cortex skill instead. Cortex v2 absorbs all librarian functionality (memory maintenance, knowledge organization, learning analysis) into a unified knowledge compiler. This skill is kept for backwards compatibility but all triggers now route to Cortex.
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
ai-agents-architect
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.
hivemind-memory
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.