1. Connect Jig to the project
Follow installation and setup, using your existing project folder. Review and save what setup adds before starting a task.2. Check the agent’s understanding
Send to your agent
For developers: what the agent reads and writes
For developers: what the agent reads and writes
jig-init reads manifests, entry points, the directory layout, and existing documents. It writes
GLOSSARY.md, ARCHITECTURE.md, and RULES.md under .ai/knowledge/, and validates them with
jig knowledge check. It asks about ambiguous boundaries and terms rather than inventing them.Setup detects verification profiles from the project’s manifests. Those profiles run your own
tools; install the project’s dependencies before expecting the checks to run.3. Bring in your existing rules
If your team already keeps architecture notes, coding conventions, or instructions for other AI tools, ask the agent to use them:Send to your agent
Proposed rules wait for your decision. They do not become instructions for future tasks just
because the agent wrote them down. You can skip this step if you have no additional rules to adopt.
For developers: links, copies, conflicts, and acceptance
For developers: links, copies, conflicts, and acceptance
This is the step that makes Jig fit a project instead of sitting beside it. Without it you would
have two sets of rules — yours and a new one — drifting apart.You say: “Map the project’s knowledge”, or “adopt our existing docs into Jig”.The agent does: first takes an inventory of what the repository already holds:
- instruction files of AI tools —
.cursorrules,.cursor/rules/,.github/copilot-instructions.md, your ownCLAUDE.md— with their Git state; - Markdown documents with their size and Git state — conventions, decision records, architecture notes;
- folders it did not open (ignored ones such as
node_modules/), named so you know what was not looked at.
Where the code shows parts the documents do not describe, it proposes domain knowledge for them
too — each statement marked as observed, inferred or proposed.Under the hood: the
jig-map skill; it works inside a task, so the agent files one first. Every
linked, copied or new document is created as proposed. A proposed document is in the
repository and in the diff, but no agent receives it: jig context resolves only accepted
knowledge. jig status counts what is waiting on its proposals: line.Where you are needed: everything. The agent shows its report and each proposed document — for a
linked document, its path and size, and the file itself on request — and waits.Accepting the proposed rules
You say: “Review the proposals.”The agent does: numbers the waiting documents, shows each one with what it claims in a sentence and what accepting it causes — which files it would apply to, and how much every future agent touching those files would have to read. You answer with numbers, “all”, or a domain name; it never asks you to type an id.Under the hood: thejig-accept skill; jig knowledge accept and jig knowledge reject.
Rejecting records the decision on the document instead of deleting it, so nobody proposes the same
thing again.Where you are needed: this is your decision alone. The agent says which proposals it is least
sure of.What happens after: an accepted document reaches every agent whose work it applies to. A
document tied to parts of the code arrives when those files are touched. A project-wide one —
your team’s ADRs, general conventions — is listed to every agent as a one-line entry it can open.
Later, when someone edits a linked file, jig status reports it on its sources changed: line
until a human has looked at the change; agents read the new text meanwhile. When an agent’s task
made the edit, its pull request says so before the merge, under Changed linked sources — need
your review.What adoption does not do yet. A rule that lives in a section of a larger file — the
“Development” part of a README — can only be linked with the whole file, or written into
RULES.md by jig-init as a copy. A new decision in a project with its own ADR folder follows
that folder’s numbering only when the agent writes it at the end of a task. And nothing migrates
your documents into Jig’s own structure: they stay yours, where they are.4. Start with a change you can check
Send to your agent
Work with tasks
Continue work, give feedback, and see what is waiting for you.
Inspect or manage it yourself
Commands for task state, context, checks, and personal settings.