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 practice-modelgit 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/practice-model)<a href="https://agentmods.dev/skills/empiricaai/empirica/practice-model"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/practice-model/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/practice-model"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/practice-model.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 | $0.00098 | $0.00895 |
| Opus 5.5 | $0.00039 | $0.00358 |
| Sonnet 5.5 | $0.00020 | $0.00179 |
| Haiku 4.5 | $0.00010 | $0.00089 |
Grade A, and why
practice-model 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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Practice model
Load it when the answer to "where does this belong, and as whom am I acting" is not obvious from the working directory.
The practice model
The prompt's IDENTITY section defines practice, practitioner and agent; the unit of identity is the practice, not the LLM, the
directory or the conversation. Two more terms matter here: a client / contact is an entity the practice serves, and an
engagement is a scoped piece of work for one. The identity and status of both live in crm-mcp, not in entity_registry.
Entity registry as the shared substrate
~/.empirica/workspace/workspace.db holds an entity_registry of the practices
(entity_type='project') and users across the org. entity_memberships (M:N) holds
typed relationships — member-of, serves, uses, owns.
Organizations, contacts and engagements are not registry state any more. Core's
CRM projection was retired (commit fcf442110): crm-mcp is the canonical store
(empirica-workspace org|contact|engagement, or the crm_* tools). Old
organization, contact and engagement rows may still sit in the registry; their
ids are valid join targets, but their name and status are stale. Do not read them
with entity-show; ask crm-mcp. What the practice learned about a client lives in
its own epistemic graph (empirica-workspace entity knowledge --entity ...).
Vocabulary vs storage: the table stores entity_type='project'; the concept is
"practice". Both are correct — one is the literal value, one is the load-bearing
idea. Future types (ai, agent, skill) are not populated, so don't claim them as
current state.
Walk it from any node: entity-list (by type/status) · entity-show <type:id> (one
entity plus its edges) · entity-walk <type:id> [--depth N] (BFS, cycle-protected) ·
entity-search <query>. All take --output {human|json}.
When practice ≠ working directory
.empirica/project.yaml's ai_id is canonical; filesystem location is incidental.
The Sentinel, calibration and inbox routing all follow ai_id.
What ships with it
1 file 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.
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.
- 2d ago First seen · 64 lines · 98 tokens per session scan A ab477ba59798
practice-model is a skill published in the GitHub repository EmpiricaAI/empirica (253 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 895 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 2026-10-26.
Other skills, from other repositories
todoist
Manage Todoist tasks, projects, and labels via official CLI.
asana
Manage Asana tasks, projects, and workspaces via MCP.
request-progress
Group recent conversations into overall requests, review each one's progress from memory, link each to the owner goals it serves, and write the build story, so My Work shows progress meters, shipping velocity and learned working preferences. Use when asked to "group requests", "group by overall request", "review…
owner-goals
Map what the owner wants from the prompts they typed themselves (prompts an agent wrote are left out), then put their top priorities and open asks, each with dated quotes, in the Goals panel at the top of My Work. Use when asked for "owner goals", "my goals", "what do I want", "what am I asking for", "map my prompts"…
agentflow
Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and recoverable pipeline design.
ai-dev-jobs-mcp
Search indexed AI and ML jobs, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP.