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 agentmods add rules/marcoporcellato/matryca-plumber/07-env-examplegit clone --depth 1 https://github.com/MarcoPorcellato/matryca-plumberWhat 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 | $0.00000 | $0.00821 |
| Opus 5 | $0.00000 | $0.00411 |
| Sonnet 5 | $0.00000 | $0.00164 |
| Haiku 4.5 | $0.00000 | $0.00082 |
Grade A, and why
07-env-example 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 3d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
.env.example maintenance (mandatory)
When you add, rename, or change the default of any environment variable read from os.environ / load_plumber_lint_config_from_environ / UI _ENV_KEY_MAP, update .env.example in the same task — without waiting for the user to ask.
When to update
| Trigger | Action |
|---|---|
New os.environ.get("MATRYCA_…"), _env_int, _map_bool(env, …), or _*_ENV = "…" in src/ |
Add key to .env.example in the correct tier |
Changed Python default (e.g. DEFAULT_*, _map_* fallback, dataclass default) |
Update Default (code) comment; adjust Template only if the safe install profile should change |
New Settings field → _ENV_KEY_MAP in ui_server.py |
Document under Operator essentials (UI-exposed keys) |
| Variable becomes deprecated or reserved (not read) | Move to deprecated block; add to tests/test_env_example_coverage.py _ALLOWLIST_UNREAD if still listed |
Do not edit the operator's local .env unless they explicitly ask.
File structure (two tiers)
[Header + legend]
=== OPERATOR ESSENTIALS === ← paths, LLM, thermal, map-reduce, low-priority, basic UI token
=== ADVANCED / HIGH IMPACT === ← explicit WARNING banner; mutating lint, compression, MCP, flock, limits, edge
- Operator essentials: settings mirrored in the Sovereign UI or needed on day one (
LOGSEQ_GRAPH_PATH, LLM URL/model, thermal, map-reduce,MATRYCA_PLUMBER_LOW_PRIORITY_MODE,MATRYCA_UI_TOKEN/ LAN basics). - Advanced / high impact: mutating graph behavior, security surface expansion, diagnostics that leak data, or tuning that can corrupt prompts/cache — prefix section with a clear do not change unless you understand the risk banner.
Per-key comment block (required)
# <What it does — one sentence>. <src/module.py>
# Default (code): <value when unset/empty in Python>
# Template: <value on the line below for new installs; omit line if same as Default (code)>
# Range / notes: <clamps, security, when to enable> (optional)
KEY=value
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.
- 3d ago First seen · 61 lines · 0 tokens per session scan A d11f258d62e3
07-env-example is a cursor rule published in the GitHub repository MarcoPorcellato/matryca-plumber (96 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 821 tokens. 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 cursor rules, from other repositories
aionforge-memory
Aionforge Memory cadence and vocabulary — recall first, capture as you go, track tasks as work items.
chronos
Time-awareness for coding agents. Consult shell clock + file mtimes before reasoning about "when" or "how long ago". No hooks on Cursor — degraded mode only.
codebase
Forensic codebase brief for AI agents.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
titanclip-monorepo
TitanClip pnpm monorepo layout, scripts, and scoping.
titanclip-cursor-adapter
Cursor local adapter — CLI integration and skills sync.