Who it is forA knowledge-base operator starting long-running, multi-batch agent work that must survive interruptions.
The problemLarge corpus changes done without a confirmed plan and persistent queue are hard to resume and audit.
The outcomeThe task identity, scope, Standards, and batch manifests are recorded once, and the Queue is compiled and checked.
What you need first
- Python 3 available as python3
- A Cambium source checkout
- A Git repository for the knowledge corpus, since adoption resolves an upstream ref to a Git commit SHA
- Terminal access for the agent, with the operator's permission to install the toolchain
- An operator who can answer the repository decisions Cambium leaves to the operator
Steps
- Copy the template with
cp Tools/schemas/task_plan.template.yaml .cambium/deltas/task-plans/TP-001.yamland complete it with the operator. (inferred, check the README) - Run
python3 Tools/init_state.py . --plan .cambium/deltas/task-plans/TP-001.yamlas a dry run, then add--apply. (inferred, check the README) - Run the exact
compile_queue.pycommand printed by init_state.py, which carries the Queue revision and SHA256 bound to the Task Plan. - Run
python3 Tools/check_queue.py .andpython3 Tools/render_queue.py .to verify and view the Queue.
Prompt for your agent
In the Cambium repo at <repo-path>, help me complete a Task Plan at .cambium/deltas/task-plans/TP-001.yaml for the corpus at <target-path>, then run the dry-run init_state.py command. Report the printed compile_queue command and the check_queue result, and do not apply anything without my confirmation.
Caveat. Cambium does not ship agent dispatch or scheduling, so the Queue records work and evidence but agents still have to be run and supervised by the operator.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page