Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 15 additions & 4 deletions doc/scheduled-routines.md
Original file line number Diff line number Diff line change
Expand Up @@ -48,10 +48,21 @@ connected for cloud sessions) is cleared, and both routines exist:
| Weekly maintenance | `trig_01VgDQW3FWV5Ln4HUutsHBRt` | `0 6 * * 1` |
| Monthly constitution audit | `trig_01RoxWz7WbEqtHxe4y62A99M` | `30 6 1-7 * 1` |

Both run `claude-sonnet-5` in the Default cloud environment against this repo, with
tools limited to `Bash, Read, Glob, Grep, Edit, Write, TodoWrite` — no browser or MCP
tools, which is the mechanical half of "provably excludes Layer 4". Manage them at
https://claude.ai/code/routines.
Both run `claude-sonnet-5` in the Default cloud environment against this repo.
**Corrected 2026-10-12 (issue #654):** there is no tool allowlist on either trigger.
Querying the trigger definitions directly (`mcp__Claude_Code_Remote__get_trigger` /
`list_triggers`) shows both carry the full session tool surface — `Bash`, `Agent`,
`Artifact`, `Workflow`, `ToolSearch`, `ScheduleWakeup`, `SendUserFile`, `Skill`,
`ListAgents`, the `github` MCP server, plus nine more MCP connectors (`Google_Calendar`,
`Slack`, `Gmail`, `Google_Drive`, `Figma`, `Vercel`, `Linear`, `Claude_Code_Remote`,
`Format`) each with an empty `permitted_tools` (i.e. unrestricted). There is **no

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Verify connector access before calling it unrestricted

An empty permitted_tools field does not by itself establish that every connector tool is callable; current remote-trigger behavior has also treated [] as “nothing permitted,” and attached connectors can remain filtered or approval-gated (upstream reproduction). The trigger definitions therefore support saying these connectors are attached, but not that the routines carry their unrestricted runtime tool surface without verifying a fired session. This distinction matters when this section is used as the routine's access/threat inventory.

AGENTS.md reference: AGENTS.md:L154-L154

Useful? React with 👍 / 👎.

mechanical exclusion of Layer 4** — `Bash` alone is sufficient to invoke
`layer4cdp`/`dev-rig`/the sweeps. The "never run Layer-4, never message a live chat
host" guarantee is enforced entirely by this file's routine prompt (the HARD RULES
each fired session is instructed to follow), the same trust basis as every other
"never" in `AGENTS.md`, not a tool-level allowlist. Treat "hermetic" as a prompted
behavior, not a provable one, until/unless the trigger's `mcp_connections` are
actually pared down. Manage the triggers at https://claude.ai/code/routines.
Comment on lines +63 to +65

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Keep hermeticity conditional on blocking the Bash paths

The until/unless qualification implies that paring down mcp_connections would make hermeticity mechanically provable, but the preceding sentence correctly notes that Bash alone can launch layer4cdp, dev-rig, or the sweeps. Even with every MCP connector removed, the unattended routine retains the exact real-host path forbidden by the repository policy, so mechanical exclusion must also block those Bash executions or their required capabilities rather than treating connector removal as sufficient.

AGENTS.md reference: AGENTS.md:L49-L49

Useful? React with 👍 / 👎.


To (re)create one, use the `RemoteTrigger` tool with `action: "create"` and the prompt
below. **The repository goes in `job_config.ccr.session_context.sources`**, as
Expand Down
Loading