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-transactiongit 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-transaction)<a href="https://agentmods.dev/skills/empiricaai/empirica/epistemic-transaction"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/epistemic-transaction/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-transaction"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/epistemic-transaction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 214 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00096 | $0.04246 |
| Opus 5 | $0.00048 | $0.02123 |
| Sonnet 5 | $0.00019 | $0.00849 |
| Haiku 4.5 | $0.00010 | $0.00425 |
Grade A, and why
epistemic-transaction scanned grade A with 1 finding 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 13d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"grounding": "ran", "ref": "curl -H 'Authorization: ...' /health → 401 before handler log"}, How it starts
The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epistemic Transaction Planning
Turn tasks into measured work. Investigation and implementation happen inside ONE measurement window, artifacts are recorded as you go, and learning compounds across boundaries.
PREFLIGHT → [noetic: investigate] → CHECK → [praxic: implement] → POSTFLIGHT
Use this instead of EnterPlanMode for non-trivial work.
Plan before you open
Decompose FIRST. A task added after the work is done is a self-graded checkbox, not a tracked unit.
empirica goals-create --objective "<title, ≤256>" --description "<markdown body>"
empirica goals-add-task --goal-id <ID> --description "<one unit of work>"
empirica goals-complete-task --task-id <ID> --evidence "commit abc123, tests pass"
--description is the rich body (≤8000 chars, markdown — the extension renders it).
Use it for anything substantive: why this exists, success criteria, links. Title-only
goals are for genuinely trivial work.
--evidence is what makes a task grounded rather than self-reported. Tie it to a
commit SHA, a test result, a file path — something deterministic.
Decompose into tasks when the work spans several files, investigation precedes implementation, or it will produce ≥2 commits. Anything you would otherwise track in a TodoWrite belongs here instead, where calibration can see it.
Lifecycle verbs, all reversible — a mis-close is recoverable, so you need not be perfect at the completion boundary:
empirica goals-create --objective "Future: X" --status planned # queued, not started
empirica goals-reopen --goal-id <ID> --reason "scope wasn't actually done"
empirica goals-archive --older-than 30 --apply # dry-run without --apply
empirica goals-list --status completed --include-archived
Add --project-id <name-or-uuid> to log against a different project.
Sizing: bug fix or single function → 1 transaction. Feature across 2–3 files → 1–2. Cross-cutting concern → 2–3. "Redesign the system" → split further.
PREFLIGHT — open the window
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.
- 13d ago First seen · 379 lines · 96 tokens per session scan A 15d0e03400f4
epistemic-transaction is a skill published in the GitHub repository EmpiricaAI/empirica (246 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 4,246 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
workflow-builder
Design, build, and maintain autonomous OpenClaw workflows (stewards). Use when creating new workflow agents, improving existing ones, evaluating automation opportunities, or debugging workflow reliability. Triggers on "build a workflow", "create a steward", "automate this process", "workflow audit", "what should I…
smart-delegation
Intelligent task delegation — route to think with deep reasoning for hard problems, or Grok for unfiltered takes. Teaches when to escalate, how to pack context into sub-agent spawns, and how to communicate delays transparently. Default: handle directly on chat (thinking off). Escalate only when the quality gain…
review
A pause before an artifact goes into the world. Reviews external comms, money, calendar, public posts, or send-as-operator actions through a small panel of independent lenses (empathy first) and returns a verdict of pass / edit / hold / block.
claude-code
Route real repo work to Claude Code instead of editing by hand. Triggers on "claude code" or "cc", and on any request to edit, fix, refactor, or open a PR in a repo outside /.openclaw/workspace. Claude Code picks up the repo's CLAUDE.md / AGENTS.md, applies its standards, and knows the /ai-coding-config:multi-review…
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.
drive-to-done
Drive a task all the way to a verified done state — write DoD first, verify each item with evidence, stop only at named stop conditions.