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 empirica-constitutiongit 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/empirica-constitution)<a href="https://agentmods.dev/skills/empiricaai/empirica/empirica-constitution"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/empirica-constitution/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/empirica-constitution"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/empirica-constitution.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 | $0.00116 | $0.04282 |
| Opus 5 | $0.00058 | $0.02141 |
| Sonnet 5 | $0.00023 | $0.00856 |
| Haiku 4.5 | $0.00012 | $0.00428 |
Grade A, and why
empirica-constitution 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 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.
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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Empirica Constitution — Deep Governance
The layer underneath the system prompt's operational routing: the questions it deliberately leaves out so it stays small.
- What counts as done? Phase-aware completion (§I)
- How do lessons interact with new findings? Cognitive immune system (§II)
- Are the rules self-applicable? The turtle principle (§III)
- How should artifacts be TYPED and CONNECTED? The graph is the artifact (§III-b)
- What IS a practice, vs a Claude / a directory / a project? (§IV)
- How do practices relate as a team? Mesh discipline (§V)
- How is sustained multi-practice coordination held, and why is it gated? (§VI)
What lives elsewhere. This list used to include artifact logging and search routing — both of which this document actually covers (§III-b, §IV) — while the system prompt was simultaneously routing them here. A reader following either pointer landed back where they started, passing over the section that answers them. Corrected in both directions:
| You need | Go to |
|---|---|
| Transaction lifecycle, PREFLIGHT/CHECK/POSTFLIGHT payloads | system prompt §TRANSACTION DISCIPLINE, then /epistemic-transaction |
| Which action needs CHECK | system prompt §NOETIC FIREWALL |
| Mesh comms mechanics — addressing, acks, proposal shape | the Cortex mesh layer (proprietary); where your install has it: /cortex-mailbox-send, /cortex-mailbox-poll |
| Correcting or retiring existing artifacts | /epistemic-gardening |
Artifact typing and graph discipline is §III-b below — this document owns it. Practice and project routing is §IV. Escalation is §V.
§I. Phase-aware completion
"Done" means different things in each phase, and conflating them is common:
| Phase | Question | 1.0 means |
|---|---|---|
| NOETIC | "Have I learned enough to proceed?" | Sufficient understanding to transition |
| PRAXIC | "Have I implemented enough to ship?" | Meets the stated objective, ready to commit |
Investigating → NOETIC. Writing code → PRAXIC. CHECK returned investigate →
NOETIC; proceed → PRAXIC.
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 · 367 lines · 116 tokens per session scan A 296059526a83
empirica-constitution is a skill published in the GitHub repository EmpiricaAI/empirica (246 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 4,282 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
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.