Rules for trusted NanoClaw groups. Shared memory, session bootstrap, cross-group memory updates. Loaded for trusted and main containers only.
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Rules for trusted NanoClaw groups. Shared memory, session bootstrap, cross-group memory updates. Loaded for trusted and admin scope.
tessl install jbaruch/nanoclaw-trustedTessl imports the complete bytes of every declared rule. Frontmatter narrows applicability at the model layer: always-on rules apply universally; conditional rules apply when their applyTo: clause matches the task.
| Rule | Scope | Summary |
|---|---|---|
| compaction-aware-summaries | conditional | When Claude Code compacts context, the summary must preserve information that cannot be recovered from files alone. |
| daily-discoveries-rule | conditional | When you learn something new and operationally important — a workflow, where something lives, how something works, a tool to use for a specific task — immediately write it to /workspace/trusted/memory/daily_discoveries.md: |
| ground-truth-trusted | conditional | Inline trusted verification sources, Google boundaries, authenticated GitHub rechecks, and computation requirements; extends core ground-truth. |
| github-data-via-gh | conditional | GitHub state — PRs, issues, repo contents, workflow runs — comes from the gh CLI inside the container (orchestrator forwards GITHUB_TOKEN per jbaruch/nanoclaw#565). curl https://api.github.com/... is still wrong (unauthenticated); gh is the only path, with no fallback. |
| identity-dual-handle | always-on | Deploy-tier extension of the dual-handle invariant in jbaruch/nanoclaw-core rules/core-behavior.md. |
| installed-content-immutable | conditional | Installed skills and rules under /home/node/.claude/skills/ and /home/node/.claude/.tessl/ are kernel-level read-only at runtime — Write/Edit against them returns EROFS. Real changes flow through the staging → promote → publish → update pipeline. |
| local-context-anchoring | always-on | Anchor every relative time/place phrasing (today / yesterday / now / here, plus Russian equivalents) to the user's local frame from the orchestrator-injected <context> tag's local_datetime / weekday / location_* attrs — not the server clock and not UTC. |
| memory-file-locations | conditional | 1. All typed memory files go in /workspace/trusted/ root — never in /workspace/trusted/memory/. The memory/ subdirectory is ONLY for daily logs and daily_discoveries. |
| messages-db-schema | conditional | Inline query, key, mutation, and drift constraints; read the installed schema inventory before selecting columns. |
| no-orphan-tasks | conditional | Before scheduling any new recurring task, check: |
| no-silent-defer | always-on | Requires a concrete handoff, truthful verification state, and a surfaced skip summary for incomplete work. |
| proactive-fact-saving | always-on | Personal facts mentioned in conversation must be saved to trusted memory IMMEDIATELY — not at end of session, not during archival, not "when non-trivial." At first mention. |
| session-bootstrap | conditional | Interactive sessions invoke tessl__trusted-memory to load memory, gated by the per-session sentinel. Scheduled prompts start with their task skill, then register the session without bootstrap reads. |
| async-tasks-extended | always-on | Trusted-tier extension of the core async-tasks protocol — reaction upgrade, background-agent spawn, scheduled-task silence, post-compaction restart. |
| container-trust-levels | always-on | Runtime detection is the contract: read-only-filesystem error = untrusted container, don't retry. Full capability matrix ships with system-status. |
| context-bootstrap-bg-agents | conditional | Background-agent prompts must include workspace context (paths, send-message tool, Telegram HTML formatting). |
| duplicate-prevention | always-on | Before creating any resource, check if it exists. Duplicate found → update existing. |
| global-memory | always-on | /workspace/global/CLAUDE.md for cross-group facts. Only update when explicitly asked. |
| humanize-outbound-prose | conditional | Run tessl__blog-writer's humanization pass on every email draft, or other prose sent under the operator's name, before posting it; talk abstracts, other speakers' too, go through tessl__cfp-abstract first as one text. |
| identity-compaction-recovery | conditional | After context compaction, re-read /workspace/global/SOUL.md — your persona context is gone. |
| pending-response-tracking | always-on | Stamp session-state.json with pending_response, do the work, send, clear. Heartbeat picks up interrupted responses. |
| proactive-participation | always-on | In trusted groups you're a participant — chime in when useful. Default-silence still applies; a reaction alone is complete participation. |
| reply-threading | always-on | Always reply-thread user messages using reply_to. Required for heartbeat to track unanswered messages. |
| skills-policy | always-on | If a skill exists, invoke it with Skill(skill: "name"). Never read SKILL.md files manually or paste content into Agent prompts. No improvising. |
| wiki-awareness | conditional | Consult or file knowledge when ingesting sources, answering questions, or producing reusable answers. |
| Skill | Description |
|---|---|
| status | User-facing /status health report — session context, container uptime, workspace mounts, tool availability, scheduled-task snapshot. Adopted from nanoclaw-core (core#68) so its workspace/mount/IPC detail only mounts in trusted and main containers. Complements system-status (orchestrator-DB probe), it does not replace it. |
| system-status | Read-only system-status probe for trusted-tier NanoClaw containers — surfaces stuck scheduled tasks, DB size, and recent task-run failures from the orchestrator's SQLite. Use as part of heartbeat or standalone. Renamed from check-system-health (which collided with the admin tile's same-named skill, per nanoclaw-admin#65); admin keeps the canonical full health probe with dismiss-mechanism management. |
| trusted-memory | Session bootstrap and rolling memory updates for trusted containers. On session start, reads MEMORY.md (permanent facts), RUNBOOK.md (operational workflows), recent daily and weekly logs, and highlights.md to restore context. After non-trivial interactions, appends timestamped entries to group-local and cross-group shared daily logs. Use when starting a new session to load previous notes and remember context, or after meaningful conversations to save conversation history, persist session state, or record newly learned owner preferences. |
| google-ops | Read-only Google Calendar and Tasks over the OneCLI gateway. Ground Truth carries source selection and tier restrictions. |
See CHANGELOG.md for version history.
Renovate is this repo's only dependency scanner. Its native
pip requirements
and GitHub Actions
managers cover requirements-dev.txt and .github/workflows/. Automatic update
PRs are scheduled before 6am on Monday (UTC), with chore(deps) commits and at
most five concurrent PRs. Minor, patch and digest updates share one PR.
Major updates open PRs on the same Monday schedule, with no dashboard approval.
prConcurrentLimit: 5 caps concurrent PRs.
See Renovate's configuration validation guide for validator usage.
Deleting dependabot.yml does not disable
Dependabot security updates
enabled in repository settings. The fleet review trigger
skips Dependabot and fork PRs, which lack access to the
Actions dispatch secret.
The scheduled coding-policy review covers these PRs.
tessl.json declares this repo's dev-time plugin dependencies.
jbaruch/* dependency floats at latest (Runtime-Managed Manifest Carve-Out, jbaruch/coding-policy: dependency-management).finsi/codex-review is third-party and pins. No dependency scanner covers the tessl ecosystem. Renewal cadence: quarterly — run tessl outdated and bump the pin in its own commit.