@aicopycoders/exodus 2026.9.1400-beta.0 → 2026.9.1400-beta.1

package/assets/docs/CLAUDE.md

@@ -64,6 +64,7 @@ These are the **Exodus** pipelines — the automatic system that drives the Gene
 | **Video** | `exodus-video` | Make a video ad from a Show: start a run from a script, read and approve the storyboard, `npx @aicopycoders/exodus video pull` every piece (per-scene clips, voices, keyframes, word timings, music bed) plus a manifest, cut them with the bundled first-cut script, upload the cut and approve it. Admin-only. |
 | **Browse** | `exodus-browse` | View history and retrieve past outputs |
 | **Drive** | `exodus-drive` | Read/write Google Docs, Sheets, and Drive files via `npx @aicopycoders/exodus drive` (uses the dashboard's Google OAuth — no local CLI) |
+| **Swipe / Mining** | (no skill; CLI only) | The competitor watch list behind the Mining page: `npx @aicopycoders/exodus swipe brands list`, `swipe brands bulk-import <csv>` (checks each brand and starts collecting its ads), `swipe brands add "<Name>" --fb <pageId>` (adds without starting research, #1366), `swipe run` / `swipe mine`. There is no `competitors` verb. |
 | **Ads** | `exodus-ads` | Read your own live Meta ads once the account is connected on the dashboard — `npx @aicopycoders/exodus ads list` (sort by cost per result, spend or CTR), `ads show <adId>` (copy, both windows, media links, comment counts), `npx @aicopycoders/exodus comments list` (already commenter-redacted), and `npx @aicopycoders/exodus winners definition` (what this brand means by a winner). Read-only; no Meta login or MCP needed. |
 | **Winners** | `exodus-winners` | Mine your own Meta ad account for winning ads and import them into Exodus as generative fuel — interview, visual confirmation, `npx @aicopycoders/exodus winners import`. A brand whose Meta account is connected reads its ads and its winner definition straight from Exodus; only an unconnected brand needs the Meta Ads MCP. |
 

package/assets/skills/exodus/SKILL.md

@@ -39,6 +39,7 @@ This skill ROUTES. Read what the user wants, name the destination skill, and han
 | Build a bot or a workflow prompt node | `bot-builder` |
 | "remember that", "never do that again" | `remember-that` |
 | "handoff", "wrap up", "what did we do today" | `handoff` |
+| Add competitors to the Mining page / watch list, see who is on it ("add these brands to mining", "put Brace Direct on the watch list") | run `npx @aicopycoders/exodus swipe brands bulk-import <csv>` (one brand: `swipe brands add "<Name>" --fb <pageId>`; `swipe brands list` to see the list). There is no `competitors` verb. |
 | Update the CLI + skills ("update exodus", "run an exodus update") | run `npx @aicopycoders/exodus@latest update` — the ONLY command that refreshes skills; `doctor` checks health but never rewrites them |
 
 The method skills above are Luke's thinking as skills; they run as a conversation and are listed in `CLAUDE.md` under **Method skills**. If a custom pipeline skill is installed in this folder (any additional `exodus-*` directory under `.claude/skills/`), it routes the same way — match the user's words to that skill's description.

package/assets/skills/find-competitors/SKILL.md

@@ -7,7 +7,7 @@ description: Find the competitors that are actually strong (scaling and working)
 
 A competitor is worth following when they are scaling and working, not when they are in the same category. The test is measurable and the search is by mechanism. Everything else here exists to make the first hour not depend on knowing the tools.
 
-Think mode until the plan-back. The sweep and the signal check are build bursts: say the plan and the cost back in two lines, get the go, run them comprehensively, write files as they land, report spend. Then back to a short list he can cut. Read the `thinking-vs-build` skill if installed.
+Think mode until the plan-back. The sweep and the signal check are build bursts: say the plan and the cost back in two lines, get the go, run them comprehensively, write files as they land, report spend. Then back to a short list the user can cut. Read the `thinking-vs-build` skill if installed.
 
 ## What "strong" means
 
@@ -128,6 +128,8 @@ Thresholds used: <…>. Verdict: FOLLOW 3+ · WATCH 2 · SKIP 0–1.
 
 The sheet lives in the folder. The FOLLOW rows become the watch list: an Ad Library page link per brand (the shape above) saved as a links file the rip can consume, and the brands added to Atria's followed list by hand in the app. When the brand is set up in Exodus, the Scout feed covers the Instagram side.
 
+**Push the watch list into Exodus (the Mining page).** The CLI verb is `npx @aicopycoders/exodus swipe brands`, not `competitors`. Write the FOLLOW rows as a CSV (`name,igHandle,fbPageId,category[,website][,youtubeHandle]`; the Ad Library `view_all_page_id` is the `fbPageId`) and run `npx @aicopycoders/exodus swipe brands bulk-import <file.csv>`: it checks each brand's page on the member's own Scrape Creators key and starts collecting its ads. `swipe brands add "<Name>" --fb <pageId>` adds one brand but does not start the research yet (open issue #1366), so prefer the CSV route even for one brand. `swipe brands list` shows what is on the page.
+
 ## Hand-offs
 
 - **Rip:** the FOLLOW rows and their longest-running ads go to the swipe process (transcript, headline, body, rank, on-screen text) and into the ad bank next to the brand's own ads.

package/assets/skills/find-competitors/scripts/adlib_sweep.py

@@ -11,6 +11,7 @@ lanes.txt: one query per line (the outcome × mechanism × ingredient grid, see
 
 Needs APIFY_API_TOKEN in .env. Cost: the apify~facebook-ads-scraper actor bills per result; 30 lanes × 150
 results is a few dollars. Without --yes the script prints the plan and stops; say it back, get a go, rerun with --yes.
+A lane that already has a JSON file is skipped, so a rerun after failures only bills the failed lanes.
 
 Output:
   <outdir>/<lane>.json          raw ads per lane
@@ -37,15 +38,22 @@ def run(kw, outdir, limit, country, tok):
     u = ("https://www.facebook.com/ads/library/?active_status=active&ad_type=all&country=" + country +
          "&q=" + urllib.parse.quote(kw) + "&search_type=keyword_unordered&media_type=all")
     path = os.path.join(outdir, kw.replace(" ", "_").replace("/", "-") + ".json")
+    if os.path.exists(path):
+        print(f"{kw:<40} already swept, skipped (delete the file to redo)", flush=True)
+        return True
     try:
         r = requests.post(f"https://api.apify.com/v2/acts/apify~facebook-ads-scraper/run-sync-get-dataset-items?token={tok}&timeout=600",
                           json={"startUrls": [{"url": u}], "resultsLimit": limit}, timeout=(30, 660))
-        d = r.json() if r.status_code == 200 else []
-        if not isinstance(d, list): d = []
+        r.raise_for_status()
+        d = r.json()
+        if not isinstance(d, list):
+            raise ValueError(f"unexpected response shape: {type(d).__name__}")
         json.dump(d, open(path, "w"))
         print(f"{kw:<40} {r.status_code} {len(d)} ads", flush=True)
+        return True
     except Exception as e:
-        print(kw, "ERR", e, flush=True)
+        print(f"{kw:<40} FAILED {e}", flush=True)
+        return False
 
 
 def aggregate(outdir):
@@ -75,7 +83,7 @@ def aggregate(outdir):
 
 def main():
     ap = argparse.ArgumentParser()
-    ap.add_argument("--keywords", required=True)
+    ap.add_argument("--keywords", help="one query per line; required unless --aggregate-only")
     ap.add_argument("--outdir", default="adlib")
     ap.add_argument("--limit", type=int, default=150)
     ap.add_argument("--country", default="US")
@@ -85,6 +93,7 @@ def main():
     a = ap.parse_args()
     os.makedirs(a.outdir, exist_ok=True)
     if not a.aggregate_only:
+        if not a.keywords: sys.exit("--keywords <file> is required for a sweep")
         tok = os.environ.get("APIFY_API_TOKEN") or sys.exit("APIFY_API_TOKEN not found in .env or environment")
         lanes = [l.strip() for l in open(a.keywords) if l.strip() and not l.startswith("#")]
         if not a.yes:
@@ -92,7 +101,13 @@ def main():
             print(f"Outputs land in {a.outdir}/. Nothing was run. Say the plan back, get a go, then rerun with --yes.")
             sys.exit(2)
         with ThreadPoolExecutor(a.workers) as ex:
-            list(ex.map(lambda k: run(k, a.outdir, a.limit, a.country, tok), lanes))
+            ok = list(ex.map(lambda k: run(k, a.outdir, a.limit, a.country, tok), lanes))
+        failed = [k for k, good in zip(lanes, ok) if not good]
+        if failed:
+            print(f"\n{len(failed)} of {len(lanes)} lanes failed; not aggregating an incomplete sweep.")
+            print("Rerun the same command with --yes: finished lanes are skipped, only the failed ones are billed again.")
+            print("Failed: " + ", ".join(failed))
+            sys.exit(1)
     aggregate(a.outdir)
 
 

package/assets/skills/find-competitors/scripts/competitor_signals.py

@@ -64,9 +64,9 @@ def get(path, params, tries=5):
 
 def search_brand(name):
     items = get("/brand-library/search", {"keyword": name, "page_size": 8}).get("items", [])
-    first = name.lower().split()[0]
-    exact = [i for i in items if i.get("name", "").lower() == name.lower()]
-    close = [i for i in items if first in i.get("name", "").lower()]
+    want = name.lower().strip()
+    exact = [i for i in items if i.get("name", "").lower().strip() == want]
+    close = [i for i in items if want in i.get("name", "").lower()]
     if exact or close:
         return (exact or close)[:1]
     # no name match: do not guess. Report what Atria returned so the user can pick.
@@ -151,6 +151,8 @@ def main():
         time.sleep(1.0)
     order = {"FOLLOW": 0, "WATCH": 1, "SKIP": 2}
     rows.sort(key=lambda r: (order.get(r.get("verdict"), 3), -(r.get("active_total") or 0)))
+    for target in [a.out, a.json]:
+        if target and os.path.dirname(target): os.makedirs(os.path.dirname(target), exist_ok=True)
     with open(a.out, "w") as f:
         f.write(f"# Competitor sheet ({dt.date.today()})\n\nVerdict: FOLLOW = 3+ strong signals · WATCH = 2 · SKIP = 0–1. Thresholds: {STRONG}\n\n")
         f.write("| Brand | Verdict | Active | Longest (d) | Launches 30d | Reuse | Offer | Strong on | Longest-running ad |\n|---|---|---|---|---|---|---|---|---|\n")

package/dist/commands/swipe.js

@@ -307,7 +307,14 @@ async function runBrandsAdd(positional, flags) {
         console.log(formatError(res));
         process.exit(1);
     }
-    console.log(`Added "${name}".`);
+    if (res.data.researching) {
+        console.log(`Added "${name}". Finding its Ad Library page and mining its ads now.`);
+    }
+    else {
+        console.log(`Added "${name}".`);
+        if (res.data.warning)
+            console.log(`  ${res.data.warning}`);
+    }
 }
 async function runBrandsRemove(positional) {
     const id = positional[0];

package/dist/lib/layout.js

@@ -97,6 +97,7 @@ export function ensureBrandDir(root, brand) {
     const created = !fs.existsSync(path.join(dir, BRAND_MARKER_FILE));
     fs.mkdirSync(path.join(dir, "state"), { recursive: true });
     fs.mkdirSync(path.join(dir, "output"), { recursive: true });
+    fs.mkdirSync(path.join(dir, "inputs"), { recursive: true });
     const marker = { slug: brand.slug, name: brand.name ?? brand.slug };
     const markerPath = path.join(dir, BRAND_MARKER_FILE);
     const existing = readBrandMarker(dir);

package/dist/lib/scaffold.js

@@ -115,6 +115,7 @@ export function ensureBaseDirs(root) {
     if (!fs.existsSync(keep))
         fs.writeFileSync(keep, "");
     fs.mkdirSync(path.join(root, "state"), { recursive: true });
+    fs.mkdirSync(path.join(root, "inputs"), { recursive: true });
     const exodusDir = path.join(root, ".exodus");
     fs.mkdirSync(exodusDir, { recursive: true });
     const statePath = path.join(exodusDir, "state.json");

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aicopycoders/exodus",
-  "version": "2026.9.1400-beta.0",
+  "version": "2026.9.1400-beta.1",
   "description": "CLI + Claude Code skills for the Copycoders Exodus ad pipeline",
   "repository": {
     "type": "git",