improve agent CI matrix, token permissions, and waitlist follower backfill (#313)

* add workflows permission to git token and waitlist improvements

- add `workflows` to `InstallationTokenPermissions` type in both action and API token routes
- include `workflows: write` in the git token so agents can push workflow file changes
- add `githubFollowers` field to WaitlistSignup schema with migration
- add script to populate waitlist followers from GitHub API
- add frog-green-square-border logo asset

Co-authored-by: Cursor <cursoragent@cursor.com>

* improve CI, agent logging, token permissions, and delegation guardrails

- add format check and build step to root CI job
- standardize agent model/effort log lines across all agents
- fix GitHub App permissions types to match OpenAPI schema (workflows is write-only)
- improve delegation error message to prevent subagent recursion
- demote noisy OpenCode stderr to debug level
- add subagent delegation rules to resolved instructions

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix graphql partial error handling, update delegation message, add workflow_run fixtures

Co-authored-by: Cursor <cursoragent@cursor.com>

* remove module-level env var throws that break CI build

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix logging bug and type hole from PR review

- use batch-local notFound counter so per-batch log doesn't undercount
- add workflows to WorkflowTokenPermissions so wire type matches what action sends

Co-authored-by: Cursor <cursoragent@cursor.com>

* lazy-init appOctokit to fix next build without env vars

Co-authored-by: Cursor <cursoragent@cursor.com>

* drop pnpm build from CI test workflow

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix delegate-effort test regex to match actual log format, disable fail-fast for agnostic tests

the test was matching `running \w+ with effort=auto` but the actual log
line from shared.ts is `» effort:  auto`. also temporarily set
fail-fast: false on action-agnostic so all failures surface at once.

Co-authored-by: Cursor <cursoragent@cursor.com>

* disable fail-fast in action workflow too, relax ci.test.ts to match

both workflow files now use fail-fast: false for agnostic tests so all
matrix jobs run to completion. the ci consistency test now checks that
the two workflows agree rather than requiring true.

Co-authored-by: Cursor <cursoragent@cursor.com>

* restore fail-fast: true now that all agnostic tests pass

Co-authored-by: Cursor <cursoragent@cursor.com>

* skip agent tests in CI when agent harness file didn't change

adds action/test/changed-agents.sh which reads the PR diff (via
dorny/paths-filter) and outputs only agents whose harness file was
modified. the action-agents matrix now uses this dynamic list instead
of a hardcoded array, so e.g. a PR touching only cursor.ts runs 6
jobs instead of 30.

Co-authored-by: Cursor <cursoragent@cursor.com>

* update ci.test.ts to validate dynamic agent matrix

the test now checks that the matrix references the changes job output
and that changed-agents.sh correctly discovers all agents.

Co-authored-by: Cursor <cursoragent@cursor.com>

* parallelize action jobs and use claude canary fallback for shared changes

runs action-agents in parallel with action-agnostic after root/changes, and updates changed-agents logic so shared or non-harness action runtime changes run only claude while harness-specific edits run only those changed agents.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>

utils/github.ts

@@ -53,33 +53,36 @@ function isOIDCAvailable(): boolean {
   );
 }
 
-// github installation token permission levels
 type ReadWrite = "read" | "write";
 type WriteOnly = "write";
-type ReadOnly = "read";
 
-// permission names use underscores (API format)
-type InstallationTokenPermissions = {
+/**
+ * GitHub App installation access token permissions.
+ * passed to `POST /app/installations/{id}/access_tokens` to scope the token.
+ * fields and allowed values come from the `app-permissions` OpenAPI schema.
+ * @see https://docs.github.com/en/rest/apps/installations#create-an-installation-access-token-for-an-app
+ * @see https://github.com/github/rest-api-description — components.schemas.app-permissions
+ */
+type GitHubAppPermissions = {
   actions?: ReadWrite;
   artifact_metadata?: ReadWrite;
   attestations?: ReadWrite;
   checks?: ReadWrite;
   contents?: ReadWrite;
   deployments?: ReadWrite;
-  id_token?: WriteOnly;
-  issues?: ReadWrite;
-  models?: ReadOnly;
   discussions?: ReadWrite;
+  issues?: ReadWrite;
   packages?: ReadWrite;
   pages?: ReadWrite;
   pull_requests?: ReadWrite;
   security_events?: ReadWrite;
   statuses?: ReadWrite;
+  workflows?: WriteOnly;
 };
 
 type AcquireTokenOptions = {
   repos?: string[];
-  permissions?: InstallationTokenPermissions;
+  permissions?: GitHubAppPermissions;
 };
 
 async function acquireTokenViaOIDC(opts?: AcquireTokenOptions): Promise<string> {
@@ -215,7 +218,7 @@ const checkRepositoryAccess = async (
 const createInstallationToken = async (
   jwt: string,
   installationId: number,
-  permissions?: InstallationTokenPermissions
+  permissions?: GitHubAppPermissions
 ): Promise<string> => {
   const requestOpts: { method: string; headers: Record<string, string>; body?: string } = {
     method: "POST",

utils/instructions.ts

@@ -422,7 +422,13 @@ export function resolveSubagentInstructions(
 ): ResolvedInstructions {
   const inputs = buildCommonInputs(ctx);
 
-  const subagentTaskSection = `You are operating in **${ctx.mode.name}** mode.
+  const subagentTaskSection = `You are operating in **${ctx.mode.name}** mode as a delegated subagent. An orchestrator spawned you and will read your final output to decide what to do next.
+
+### Delegation rules
+
+- The \`delegate\` tool is NOT available to you — complete your task directly using the available tools.
+- When you finish, end with a clear, concise summary: what you did, what succeeded, what failed, and any blockers or next steps. The orchestrator uses this to decide whether to delegate again or report final results.
+- If you encounter an error you cannot resolve, report it clearly — do not attempt to delegate or re-run yourself.
 
 ${ctx.mode.prompt}`;
 

utils/setup.ts

@@ -69,7 +69,7 @@ export interface SetupGitParams extends GitContext {
  * - sets up authentication via gitToken (minimal contents:write)
  * - for PR events, checks out the PR branch using shared helper
  *
- * gitToken is a minimal-permission token (contents:write only) used for git operations.
+ * gitToken is a minimal-permission token (contents + workflows) used for git operations.
  * it is assumed to be potentially exfiltratable, so it has limited scope.
  */
 export async function setupGit(params: SetupGitParams): Promise<void> {

utils/token.ts

@@ -105,12 +105,20 @@ export async function resolveTokens(params: ResolveTokensParams): Promise<TokenR
 
   // create git token based on push permission (assumed exfiltratable)
   // disabled = read-only, restricted/enabled = write (MCP tools enforce branch restrictions)
-  const gitContents = params.push === "disabled" ? "read" : "write";
-  const gitToken = await acquireNewToken({ permissions: { contents: gitContents } });
+  // workflows permission is write-only in the API, so only requested when pushing is allowed
+  const gitPermissions =
+    params.push === "disabled"
+      ? { contents: "read" as const }
+      : { contents: "write" as const, workflows: "write" as const };
+  const gitToken = await acquireNewToken({ permissions: gitPermissions });
   if (isGitHubActions) {
     core.setSecret(gitToken);
   }
-  log.info(`» acquired git token (contents:${gitContents})`);
+  log.info(
+    `» acquired git token (${Object.entries(gitPermissions)
+      .map((e) => e.join(":"))
+      .join(", ")})`
+  );
 
   // create full MCP token - not exfiltratable (only accessible via MCP tools)
   const mcpToken = await acquireNewToken();