Reference
Plugin registries
What happens with a wrong name
BRIAR_NOTIFY_SINKS or BRIAR_JOURNAL_SINKS is skipped. These lists match briar-cli 1.1.75. For your own version, run the command with -h: it prints the allowed names.- Extract
- Agent, LLM and scaffold
- Plan boards
- Storage and journal
- Logins and keys
- Messages and alerts
- Output formats
Extract
An extractor reads one kind of fact from a service and writes it as a section of a knowledge blob. Extractors get their data through the providers further down. Most read your code host. active-tickets and ticket-archaeology read your tracker, aws-infra reads your cloud, and meeting-digest reads your meeting tool.
Scheduled extractors
Where you use it: briar extract --include NAME (you can repeat it), and the extract: list of a runbook schedule. In the source: briar.extract.EXTRACTORS.
| Name | What it is |
|---|---|
active-tickets | Open tickets in your tracker projects. |
active-work | Open PRs across your repos. |
aws-infra | Your cloud setup: servers, databases, queues and logs, on AWS, Google Cloud or Azure. |
ci-health | CI pass rate, flaky workflows, and how run time changes. |
code-hotspots | Files that often change together, so the agent knows what else to look at. |
code-scanning | Open code scanning alerts, by rule and by file. |
codebase-conventions | Each repo's language, test runner, linter and migration tool. |
commit-message-quality | How well commit messages follow Conventional Commits, and how clean their subject lines are. |
defect-hotspots | Files most likely to break, scored from churn, bug fixes and size. |
dependency-health | Open security alerts on your packages, by severity. |
github-deployments | Environments, deployments and recent CI runs. |
meeting-digest | Recent meetings: a summary and the action items of each. |
pr-archaeology | Patterns in merged PRs: what reviewers look at, and who reviews. |
pr-hygiene | PR sizes, the share of big PRs, approvals with no comments, and time to first review. |
release-cadence | How often a repo ships, and when it last did. |
repo-governance | Branch rules, and whether CODEOWNERS, pre-commit and linter or editor config exist. |
revert-signals | Reverts and emergency fixes: weak spots that tests and review missed. |
review-nits | Phrases reviewers repeat across PRs. Good candidates for lint rules. |
reviewer-profile | For each reviewer: how often they comment, on which files, and what they ask for. |
stale-prs | Open PRs with no activity for a while: the review backlog. |
test-discipline | Test files per source file, and source files with no clear test. |
ticket-archaeology | Patterns in closed tickets: who takes them, and which labels, over time. |
todo-density | How many TODO, FIXME and HACK notes there are, and which files have the most. |
Task extractors
Where you use it: You do not name these. briar agent (and plan run, which calls it) runs them for the one ticket or PR it works on. In the source: briar.extract.TASK_SCOPED_EXTRACTORS.
| Name | What it is |
|---|---|
ticket-context | The full text, acceptance criteria and comments of one ticket. Used by agent implement. |
pr-review-context | The review comments and CI results of one PR. Used by agent prfix. |
meeting-context | Meeting transcripts about the task. Runs when meeting keys are set, or with --meeting-key or --meeting-query. |
slack-context | Slack threads about the task, read only. Runs when Slack keys are set, with --slack-query or the ticket key as the search. |
Code hosts
Where you use it: --provider on extract, agent and plan run, and provider under [repo] in .briar.toml. Default github. In the source: briar.extract._providers.PROVIDERS.
| Name | What it is |
|---|---|
github | GitHub. Reads GITHUB_TOKEN. |
bitbucket | Bitbucket Cloud. Reads BITBUCKET_ACME_USERNAME, _APP_PASSWORD and _WORKSPACE. In 1.1.75 the agent pushes its branch here but cannot open the PR. |
Trackers
Where you use it: --tracker on extract, agent implement and plan run, and tracker in .briar.toml. In the source: briar.extract._trackers.TRACKERS.
| Name | What it is |
|---|---|
jira | Jira Cloud, by API token or browser session. Reads JIRA_ACME_*. |
github-issues | GitHub Issues. Reads GITHUB_TOKEN. |
bitbucket-issues | Bitbucket Cloud issues. Reads BITBUCKET_ACME_*. |
linear | Linear. Reads LINEAR_ACME_TOKEN. |
Clouds
Where you use it: --cloud on extract, for the aws-infra extractor. Default aws. In the source: briar.extract._clouds.CLOUDS.
| Name | What it is |
|---|---|
aws | Amazon Web Services. Built in. |
gcp | Google Cloud. Needs pip install "briar-cli[gcp]". |
azure | Microsoft Azure. Needs pip install "briar-cli[azure]". |
AWS services
Where you use it: --aws-extract-service NAME on extract (you can repeat it). Default: all of them. In the source: briar.extract.aws_services.AWS_SERVICE_GATHERERS.
| Name | What it is |
|---|---|
ecs | ECS clusters and their services. |
rds | RDS database instances. |
lambda | Lambda functions. |
sqs | SQS queues. |
logs | CloudWatch log groups, the 10 biggest. |
tagging-inventory | Every tagged resource in the region, of any service. |
Meeting tools
Where you use it: --meeting on extract. Agent and plan run have it too, as a hidden flag. Default fireflies. In the source: briar.extract._meetings.MEETINGS.
| Name | What it is |
|---|---|
fireflies | Fireflies.ai. Reads FIREFLIES_ACME_API_KEY. |
Chat tools
Where you use it: The hidden --chat flag on agent and plan run. Default slack. briar only reads chat; there is no scheduled chat extractor. In the source: briar.extract._chats.CHATS.
| Name | What it is |
|---|---|
slack | Slack, through a browser session. Reads SLACK_ACME_TOKEN and SLACK_ACME_COOKIE_D. |
Agent, LLM and scaffold
The AI side of briar: which model company answers, which helper tools the agent always has, and the parts briar scaffold builds a config from.
LLM providers
Where you use it: --llm on plan build, plan next, plan run and chat. agent has no --llm: it always runs on Anthropic. plan build also takes an empty value, to build with no LLM. In the source: briar.agent._llms.LLMS.
| Name | What it is |
|---|---|
anthropic | Claude, by Anthropic. Reads CLAUDE_CODE_OAUTH_TOKEN or ANTHROPIC_API_KEY. |
openai | OpenAI. Reads OPENAI_API_KEY. Needs the openai extra. |
gemini | Google Gemini. Reads GEMINI_API_KEY. Needs the gemini extra. |
bedrock | Models on AWS Bedrock (Claude by default), through your normal AWS login. |
Built-in MCP servers
Where you use it: On in every agent run, including plan run and --dry-run, when pip install "briar-cli[mcp]" is done. Without the extra, briar skips them with one warning and the run goes on. Turn them off with --no-default-mcp or BRIAR_NO_DEFAULT_MCP=1. A runbook mcp: entry with the same name replaces one. In the source: briar.mcp.defaults.DEFAULT_MCP_SERVERS.
| Name | What it is |
|---|---|
think | Step by step thinking for hard tasks. Runs with npx. Without Node it is skipped with a warning. |
time | The date, the time and time zone math. Runs with uvx. Without uv it is skipped with a warning. |
Scaffold templates
Where you use it: briar scaffold NAME. In the source: briar.iac.scaffold.TEMPLATES.
| Name | What it is |
|---|---|
implementation | From a ticket to a plan, a human approval, the code, and a PR. You can change each step. |
pr-fixes | Reads PR review comments, pushes fixes and replies. No human approval step. |
Agent roles
Where you use it: --archetype on both scaffold templates. In the source: briar.iac.scaffold.archetypes.ARCHETYPES.
| Name | What it is |
|---|---|
engineer | Builds what a ticket asks for, commits, and opens a PR. |
pr-ci-fixer | Fixes failing CI on open PRs, from the failure logs. |
pr-conflict-resolver | Merges the base branch into stale PRs, fixes the conflicts, and pushes. |
pr-fixer | Answers open review comments with follow-up commits. |
triager | Sorts and labels tickets, and adds a short summary comment. |
Workflow shapes
Where you use it: --shape on both scaffold templates. In the source: briar.iac.scaffold.shapes.WORKFLOW_SHAPES.
| Name | What it is |
|---|---|
one-shot | One agent step. No approval, no branches. |
plan-approve-act | The agent plans, a person approves, then it acts. On a reject, it comments. |
triage | One agent that sorts and comments. It takes no write actions. |
Triggers
Where you use it: --trigger-kind on both scaffold templates. In the source: briar.iac.scaffold.triggers.TRIGGER_TEMPLATES.
| Name | What it is |
|---|---|
github_webhook | Starts on GitHub webhook events, like issues.opened. |
bitbucket_webhook | Starts on Bitbucket webhook events, like issue:created. |
schedule_cron | Starts on a cron schedule. Hourly by default. |
manual | No trigger. You start it by hand. |
Sources
Where you use it: --source on both scaffold templates. In the source: briar.iac.scaffold.sources.SOURCE_TEMPLATES.
| Name | What it is |
|---|---|
github | Issues from one repo. Tools to comment, open PRs and commit files. |
bitbucket | Issues and PRs from one Bitbucket Cloud repo. The same three tools. |
jira | Issues from Jira projects. Tools to comment, change status and edit. |
aws | AWS state for the agent to read. No write tools. |
sentry | Error groups from Sentry projects. Tools to comment, resolve, assign and ignore. |
Plan boards
briar plan build reads cards from a board. You pass the board's link, and briar picks the reader that matches it.
Board readers
Where you use it: The board argument of briar plan build. In the source: briar.plan._boards.BOARD_READERS.
| Name | What it is |
|---|---|
jira | A Jira board link, like https://acme.atlassian.net/jira/software/projects/ACME/boards/12, or the short form jira:ACME. |
github-project | A GitHub Projects link, like https://github.com/orgs/acme-co/projects/3 (or /users/ for a personal project). |
Storage and journal
Where briar keeps knowledge blobs and run records.
Knowledge stores
Where you use it: --store on most commands, store in .briar.toml, BRIAR_STORE, and knowledge.store in a runbook. In the source: briar.storage.KnowledgeStoreRegistry.
| Name | What it is |
|---|---|
file | Markdown files under ./knowledge. Nothing to set up. |
postgres | A Postgres database at BRIAR_DATABASE_URL, with history. |
Journal stores
Where you use it: --store on briar journal, and BRIAR_JOURNAL_STORE. In the source: briar.journal.JOURNAL_STORE_NAMES.
| Name | What it is |
|---|---|
file | One JSON file per session under ./journal/sessions/. |
Journal outputs
Where you use it: BRIAR_JOURNAL_SINKS, a comma list. An unknown name is skipped. In the source: briar.journal.sinks.JOURNAL_SINKS.
| Name | What it is |
|---|---|
file | A readable markdown copy of each session in ./journal/published/. |
Logins and keys
How briar gets keys and where it keeps them. Full details are in Auth, secrets and telemetry.
Login targets
Where you use it: The TARGET word of briar auth login, logout, refresh and status. In the source: briar.auth._acquirers.ACQUIRERS.
| Name | What it is |
|---|---|
github-device | GitHub, by typing a short code on github.com. Needs a GitHub OAuth app. |
github-pat | GitHub, by pasting a personal access token. |
bitbucket-app-password | Bitbucket Cloud, by pasting an app password. |
aws-static | AWS, by pasting an IAM access key and secret. |
aws-sso | AWS, through IAM Identity Center in the browser. Short-lived keys. |
jira-token | Jira, by pasting an API token. |
jira-session | Jira, by pasting a browser session cookie. For sites with no API tokens. |
linear-api-key | Linear, by pasting a personal API key. |
fireflies | Fireflies.ai, by pasting an API key. |
Key stores
Where you use it: --cred-store on briar auth and briar secrets doctor, and BRIAR_DEFAULT_STORE. In the source: briar.credentials.STORES.
| Name | What it is |
|---|---|
envfile | A local file, ~/.config/briar/secrets.env by default. The default, and the only one loaded when commands run. |
aws-secretsmanager | AWS Secrets Manager, as briar/NAME. |
ssm | AWS SSM Parameter Store, as /briar/NAME. |
vault | HashiCorp Vault KV v2, at secret/briar/NAME. Needs the vault extra. |
Startup loaders
Where you use it: --kind on briar secrets bootstrap. Each one that is set up also runs at the start of every command. In the source: briar.credentials._bootstraps.BOOTSTRAPS.
| Name | What it is |
|---|---|
envfile | Loads the env file into the env. Names you already set win. |
Jira login kinds
Where you use it: JIRA_ACME_AUTH_KIND. When it is empty, briar picks session if a session cookie var is set, else token. In the source: briar.extract._trackers._jira_auth._JIRA_AUTHS.
| Name | What it is |
|---|---|
token | Email and API token: JIRA_ACME_EMAIL and JIRA_ACME_TOKEN. |
session | Browser cookies: JIRA_ACME_TENANT_SESSION_TOKEN or JIRA_ACME_SESSION_TOKEN. |
Messages and alerts
Two ways briar posts outside. Messages are posts the agent makes while it works. Alerts are sent when a runbook task fails.
Message kinds
Where you use it: The kind: of each entry in a runbook company's messages: block. The agent posts with its send_message tool, only when it runs with --runbook. In the source: briar.messaging.WRITERS.
| Name | What it is |
|---|---|
github-pr-comment | A comment on a GitHub PR. Reads GITHUB_TOKEN. |
bitbucket-pr-comment | A comment on a Bitbucket PR or issue. Reads BITBUCKET_ACME_*. |
jira-comment | A comment on a Jira ticket. Reads JIRA_ACME_*. |
jira-transition | Moves a Jira ticket to another status. Reads JIRA_ACME_*. |
slack-channel | A post in a Slack channel, by webhook. Reads SLACK_ACME_WEBHOOK_URL. |
telegram-chat | A post in a Telegram chat, by bot. Reads TELEGRAM_BOT_TOKEN and TELEGRAM_ACME_CHAT_ID. |
Alert sinks
Where you use it: BRIAR_NOTIFY_SINKS, a comma list, like slack,email. An unknown name is logged and skipped. See Failure alerts. In the source: briar.notify.SINKS.
| Name | What it is |
|---|---|
email | An email over SMTP. Reads SMTP_*, EMAIL_FROM and EMAIL_ACME_TO. |
pagerduty | A PagerDuty warning. Reads PAGERDUTY_ACME_ROUTING_KEY. |
slack | A Slack post by webhook. Reads SLACK_ACME_WEBHOOK_URL. |
telegram | A Telegram message by bot. Reads TELEGRAM_BOT_TOKEN and TELEGRAM_ACME_CHAT_ID. |
Output formats
How commands print their results.
Formats
Where you use it: The global --format flag. It works anywhere on the line. Default table. In the source: briar.formatting.FORMATTERS.
| Name | What it is |
|---|---|
table | A table for lists. A single record prints as JSON. |
json | JSON. |
yaml | YAML. |
csv | Comma separated values, one row per line. |
quiet | Only the id of each row, one per line, for xargs. |
See also
- briar extract: extractors and their flags.
- briar scaffold: roles, shapes, triggers and sources in use.
- Configuration: the env vars each name reads.
- Auth, secrets and telemetry: login targets and key stores.