zubair-trabzada/ai-marketing-claude

GitHub ↗ · How this check works

Per-setup public labels: Linux / Haiku: Works · Linux / Luna: Works

Static status badge · SVG · read-only JSON. Embed with ![Coldpass status](https://coldpass.dev/badge/zubair-trabzada--ai-marketing-claude.svg).

agent-harness

Works

README claims checked out on 2 recorded setups.

Answers apply to each recorded setup, revision and operation. Earlier observations remain in Run details.

Tested on Linux
PlatformHaikuLuna
Linuxyesyes

Linux / Haiku 5.5: yes · Oct 25, 2026 · e5aa0ea4c5f3 · claude-code / 2.1.310 (Claude Code)
Recorded operation: python3 scripts/social_calendar.py 'AI automation' linkedin,twitter 7

Linux / Luna: yes · Oct 25, 2026 · e5aa0ea4c5f3 · codex / codex-cli 0.163.0
Recorded operation: python3 scripts/social_calendar.py 'AI automation' linkedin,twitter 2

Does what it says
1 of 1 claims checked out
  • Generate a 30-day social media content calendar.: Real input produced the expected result: "topic": "AI automation"

    Source: 30-day social media content calendar

    Input: AI automation; LinkedIn and Twitter; 2 days

    Expected: JSON calendar includes topic, chosen platforms and calendar entries

    Command: python3 scripts/social_calendar.py 'AI automation' linkedin,twitter 2

    Observed: "topic": "AI automation", "brand": "AI automation", "platforms": [ "linkedin", "twitter" ], "duration_days": 2, "start_date": "2026-10-25", "end_date": "2026-10-27", "posting_schedule": { "linkedin": { "ideal": "3-5x/week", "minimum": "2x/week", "best_times": "Tue-Thu 8-10am, 12pm" }, "twitter": { "ideal": "3-5x/day", "minimum": "1x/day", "best_times": "9am, 12pm, 5pm" } }, "content_pillars": { "educational": { "name": "Educational", "description": "Teach your audience something valuable", "freq

MCP
No
Local or hosted
local
Local: runs on your machine
Needs keys or browser
None seen
Maintained
Slow
slow: last commit 237 days ago; 0 commits and 0 merged PRs in 90 days; 3 open issues, 3 open PRs; 0 of 6 recent threads got a maintainer reply; no releases

Last commit Mar 1, 2026

Setup time
30 s
30 s to a working result
Issue
none found in recorded check
Examples
1 of 1 ran as expected
  • Generate a social content calendar using the script.: command completed successfully

    Source: scripts/social_calendar.py main() usage/example

    Input: AI automation, linkedin,twitter, 2

    Expected: JSON content calendar with two entries

    Command: python3 scripts/social_calendar.py 'AI automation' linkedin,twitter 2

    Observed: flow": [ "1. Create a long-form piece about AI automation (blog post or YouTube video)", "2. Extract 5-7 key insights as individual social posts", "3. Turn each insight into a platform-specific format", "4. Create a carousel/thread from the full piece", "5. Film a 60s summary as a Reel/TikTok", "6. Pull quotes for image posts", "7. Create a poll or question from one insight", "8. Share behind-the-scenes of creating the content", "9. Reshare top-performing posts 2-4 weeks later", "10. Create a 'best of' compilation monthly" ] } }

Evidence
README behavior checked
Agent interfaces
CLI
CLI

Observed interfaces were exercised by the checker. Documentation alone does not confirm compatibility.

Tested with
Codex / Luna
  • Linux: Codex / Luna · agent codex-cli 0.163.0 · Checked operation passed · Oct 25, 2026 on e5aa0ea4c5f3

Each entry describes its recorded operation and source revision.

Safety
Made outbound HTTPS connections: yes (hosts not recorded) by <guest-path>

Review signals across current setups: connection review. 2 listed items (named-host connections, static matches, dependency advisories) are below and do not change this verdict.

Repository processes attempted these non-loopback connections; proxies can hide the final hostname. 4 distinct locations. 4 attributed processes.

Source contains download and execute; review its purpose. install.sh

Reviewed as expected for a test run: attempted writes that failed, so nothing was written.

Full event, path and process lists for each observed setup:

Run details

Haiku 5.5

Native agent · Checked operation passed

Checked operation python3 scripts/social_calendar.py 'AI automation' linkedin,twitter 7

Agent-reported scope: Install the AI Marketing Suite skills with the README installer, then run the documented Python CLIs (social calendar generator and page analyzer)

Run details
run
zubair-trabzada--ai-marketing-claude-claude-haiku-5-5-1792972647555937259
date
Oct 25, 2026
time to working
54.4s
product hosting / execution
Local command in the guest
recorded operation scope
product operation
model
claude-haiku-5-5
agent / version
claude-code / 2.1.310 (Claude Code)
platform
linux
reported cost
$0.011537
Recorded source
https://github.com/zubair-trabzada/ai-marketing-claude
Backend
hyperv
Tool transport
mcp-assigned-vm
Requested source pin (not an observed revision)
{"commit": "e5aa0ea4c5f30d8bc08771e8ea932463e76d3356", "url": "https://github.com/zubair-trabzada/ai-marketing-claude"}
Test version
readme-ca496ea10bb07418d1d8f1c256c2433a55547acc0fb62d8b6d86ae33c976fbfa
revision
e5aa0ea4c5f30d8bc08771e8ea932463e76d3356
Whose fault: not assigned · resolved

Safety: Review signals: 1 connection review, 1 download and execute.

Review signals: 1 connection review, 1 download and execute.

Reviewed as expected for a test run: attempted writes that failed, so nothing was written.

Repository processes attempted these non-loopback connections; proxies can hide the final hostname. 4 distinct locations. 4 attributed processes.

Source contains download and execute; review its purpose. install.sh

OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check.

A short run cannot establish that code is safe.

Connections show IP addresses; proxies can hide the final hostname.

Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing.

Full safety evidence →

Answers recorded for this run
  • social calendar generator: Real input produced the expected result: "topic": "AI automation"

    Source: Social content calendar generator

    Input: AI automation linkedin,twitter 7

    Expected: JSON calendar for the topic

    Command: python3 scripts/social_calendar.py 'AI automation' linkedin,twitter 7

    Observed: "topic": "AI automation", "brand": "AI automation", "platforms": [ "linkedin", "twitter" ], "duration_days": 7, "start_date": "2026-10-25", "end_date": "2026-11-01", "posting_schedule": { "linkedin": { "ideal": "3-5x/week", "minimum": "2x/week", "best_times": "Tue-Thu 8-10am, 12pm" }, "twitter": { "ideal": "3-5x/day", "minimum": "1x/day", "best_times": "9am, 12pm, 5pm" } }, "content_pillars": { "educational": { "name": "Educational", "description": "Teach your audience something valuable", "freq

  • automated page analysis: Real input produced the expected result: "title": "Example Domain"

    Source: automated page analysis, competitor scanning

    Input: https://example.com

    Expected: SEO analysis with title Example Domain

    Command: python3 scripts/analyze_page.py https://example.com

    Observed: "title": "Example Domain", "title_length": 14, "title_ok": false, "meta_description": "", "meta_description_length": 0, "meta_description_ok": false, "canonical": "", "robots_meta": "", "has_viewport": true, "og_tags": {}, "headings": {}, "heading_issues": [ "Missing H1 tag" ], "images_total": 0, "images_without_alt": 0, "images_with_lazy_loading": 0 }, "content": { "word_count": 32, "headings_count": 0, "h1": [], "h2": [] }, "conversion": { "ctas": []

Examples

  • Generate a social media content calendar from the CLI: command completed successfully

    Source: scripts/social_calendar.py usage

    Input: AI automation linkedin,twitter,instagram 30

    Expected: 30-day calendar JSON for the topic

    Command: python3 scripts/social_calendar.py 'AI automation' linkedin,twitter,instagram 30

    Observed: flow": [ "1. Create a long-form piece about AI automation (blog post or YouTube video)", "2. Extract 5-7 key insights as individual social posts", "3. Turn each insight into a platform-specific format", "4. Create a carousel/thread from the full piece", "5. Film a 60s summary as a Reel/TikTok", "6. Pull quotes for image posts", "7. Create a poll or question from one insight", "8. Share behind-the-scenes of creating the content", "9. Reshare top-performing posts 2-4 weeks later", "10. Create a 'best of' compilation monthly" ] } }

Local or hosted: local

What the agent did

Install the AI Marketing Suite skills with the README installer, then run the documented Python CLIs (social calendar generator and page analyzer)

cd <guest-path> && pwd && ls -la && id -u && python3 --version && (git status 2>&1 | head -3) && echo --- && head -c 6000 README.md
cd <guest-path> && tail -c 1800 README.md; echo ---; cat requirements.txt; echo ---; ls scripts templates; echo ---; sed -n 1,60p scripts/analyze_page.py | head -80; ls <guest-path> /inputs 2>&1; curl -s -m 5 -o /dev/null -w '%{http_code}\n' $CDP_URL/json/version
cd <guest-path> && curl -s -m 5 -w '\nHTTP %{http_code}\n' $CDP_URL/json/version; echo ---; sed -n 1,80p install.sh
cd <guest-path> && grep -n "argv\|argparse\|add_argument\|__main__\|usage" scripts/*.py | head -60
cd <guest-path> && bash ./install.sh </dev/null 2>&1 | tail -25; echo "exit=${PIPESTATUS[0]}"; ls ~/.claude/skills | head -30
cd <guest-path> && sed -n 180,240p scripts/social_calendar.py
cd <guest-path> && mkdir -p <guest-path> && python3 scripts/social_calendar.py 'AI automation' linkedin,twitter 7 > <guest-path>; echo "exit=$?"; python3 -c 'import json,sys; d=json.load(open("<guest-path>")); print(list(d.keys())); print(len(d["calendar"]))' ; echo ---; timeout 40 python3 scripts/analyze_page.py https://example.com | head -c 600; echo; echo "exit=${PIPESTATUS[0]}"
cd <guest-path> && grep -rniE "cron|schedule|--once|--now|while True|webhook|daemon" --include=*.py --include=*.sh --include=*.md . | grep -v "^./skills/" | head -20; echo ---; grep -n "argv\|def main" scripts/generate_pdf_report.py | head; sed -n 415,430p scripts/generate_pdf_report.py; python3 -m venv --help >/dev/null 2>&1 && echo venv_ok
cd <guest-path> && mkdir -p .coldpass && cat > .coldpass/probe.json <<'EOF'
{"kind":"cli","argv":["python3","scripts/social_calendar.py","AI automation","linkedin,twitter","7"],"cwd":"<guest-path>","expected_text":"\"topic\": \"AI automation\""}
EOF
cat > .coldpass/claims.json <<'EOF'
[{"kind":"claim","claim":"social calendar generator","source":"README.md","quote":"Social content calendar generator","source_quote":"Social content calendar generator","input":"AI automation linkedin,twitter 7","expected":"JSON calendar for the topic","probe_kind":"cli","argv":["python3","scripts/social_calendar.py","AI automation","linkedin,twitter","7"],"expected_text":"\"topic\": \"AI automation\"","cwd":"<guest-path>"},
{"kind":"claim","claim":"automated page analysis","source":"README.md","quote":"automated page analysis, competitor scanning","input":"https://example.com","expected":"SEO analysis with title Example Domain","probe_kind":"cli","argv":["python3","scripts/analyze_page.py","https://example.com"],"expected_text":"\"title\": \"Example Domain\"","cwd":"<guest-path>"}]
EOF
cat > .coldpass/cycles.json <<'EOF'
{"detected":false,"reason":"Entry points inspected (install.sh, scripts/*.py, README.md): no cron, scheduler, loop, --once/--now, or webhook trigger. Product is run on demand via Claude Code /market commands and scripts run once per invocation.","checks":[]}
EOF
cat > .coldpass/examples.json <<'EOF'
[{"kind":"example","claim":"Generate a social media content calendar from the CLI","source":"scripts/social_calendar.py usage","input":"AI automation linkedin,twitter,instagram 30","expected":"30-day calendar JSON for the topic","argv":["python3","scripts/social_calendar.py","AI automation","linkedin,twitter,instagram","30"],"cwd":"<guest-path>","expected_text":"\"duration_days\": 30"}]
EOF
python3 -I -c 'import json;[json.load(open(f".coldpass/{n}.json")) for n in ["probe","claims","cycles","examples"]];print("json ok")'
cd <guest-path> && cat > .coldpass/claims.json <<'EOF'
[{"kind":"claim","claim":"social calendar generator","source":"Social content calendar generator","input":"AI automation linkedin,twitter 7","expected":"JSON calendar for the topic","probe_kind":"cli","argv":["python3","scripts/social_calendar.py","AI automation","linkedin,twitter","7"],"expected_text":"\"topic\": \"AI automation\"","cwd":"<guest-path>"},
{"kind":"claim","claim":"automated page analysis","source":"automated page analysis, competitor scanning","input":"https://example.com","expected":"SEO analysis with title Example Domain","probe_kind":"cli","argv":["python3","scripts/analyze_page.py","https://example.com"],"expected_text":"\"title\": \"Example Domain\"","cwd":"<guest-path>"}]
EOF
<env-var>=<guest-path> python3 -I <guest-path> --validate --replay 2>&1 | tail -60; echo "exit=${PIPESTATUS[0]}"
cd <guest-path> && rm -rf <guest-path> && cat > .coldpass/report.json <<'EOF'
{"outcome":"working","fault_owner":null,"operation":"Install the AI Marketing Suite skills with the README installer, then run the documented Python CLIs (social calendar generator and page analyzer)","operation_scope":"Linux Ubuntu guest, Python 3.12.3 standard library only (no reportlab, no Claude Code runtime). /market slash commands are Claude Code skills and were not exercised because Claude Code is not installed in the guest; the CLI scripts were exercised directly. analyze_page.py needs outbound HTTPS to the target site.","steps":["curl -fsSL https://raw.githubusercontent.com/zubair-trabzada/ai-marketing-claude/main/install.sh | bash  (replaced by the local ./install.sh from the pinned checkout, which is the README's Manual Install step)","./install.sh (exit 0; installed 14 skills, 5 agents, 4 scripts, 6 templates to ~/.claude)","python3 scripts/social_calendar.py 'AI automation' linkedin,twitter 7 (exit 0, 7-day calendar JSON)","python3 scripts/analyze_page.py https://example.com (exit 0, SEO analysis with title Example Domain)"],"deviations":["Used the local copy of install.sh from the pinned checkout instead of the curl|bash one-liner; the script itself was run as documented and was non-interactive (stdin from /dev/null).","install.sh printed literal \\x1b color escape sequences in its summary (cosmetic only; it does not affect install success).","Did not install the optional reportlab package, so generate_pdf_report.py (report-pdf) was not run.","The /market commands (audit, copy, etc.) run inside Claude Code and were not exercised; Claude Code is not present in the VM.","The checker path was <guest-path> because /inputs/coldpass-preflight.py does not exist in this guest."],"stuck_step":null,"main_blocker":null,"plain_failure":null,"suggested_fix":"None required for the scripted operations. For full use, install Claude Code and run /market commands; install reportlab for PDF output."}
EOF
python3 -I -c 'import json;json.load(open(".coldpass/report.json"));print("report ok")'; <env-var>=<guest-path> python3 -I <guest-path> --validate --replay 2>&1 | python3 -c 'import json,sys; d=json.load(sys.stdin); print(d["valid"], d["problems"], d["replay"]["status"])'; ls .coldpass
Earlier attempts (1)

Luna

Native agent · Checked operation passed

Checked operation python3 scripts/social_calendar.py 'AI automation' linkedin,twitter 2

Agent-reported scope: Generate a social media content calendar from a topic.

Run details
run
zubair-trabzada--ai-marketing-claude-gpt-6-luna-1792972738323830588
date
Oct 25, 2026
time to working
29.8s
product hosting / execution
Local command in the guest
recorded operation scope
product operation
model
gpt-6-luna
agent / version
codex / codex-cli 0.163.0
platform
linux
reported cost
not reported (not assumed free)
Recorded source
https://github.com/zubair-trabzada/ai-marketing-claude
Backend
hyperv
Tool transport
mcp-assigned-vm
Requested source pin (not an observed revision)
{"commit": "e5aa0ea4c5f30d8bc08771e8ea932463e76d3356", "url": "https://github.com/zubair-trabzada/ai-marketing-claude"}
Test version
readme-a17389bda4cc696f9601c0c4ff1b2c16e23bfa1d907883b715ccdd9e92ddec56
revision
e5aa0ea4c5f30d8bc08771e8ea932463e76d3356
Whose fault: not assigned · resolved

Safety: Review signals: 1 download and execute.

Review signals: 1 download and execute.

Reviewed as expected for a test run: attempted writes that failed, so nothing was written.

Source contains download and execute; review its purpose. install.sh

OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check.

A short run cannot establish that code is safe.

Connections show IP addresses; proxies can hide the final hostname.

Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing.

Full safety evidence →

Answers recorded for this run
  • Generate a 30-day social media content calendar.: Real input produced the expected result: "topic": "AI automation"

    Source: 30-day social media content calendar

    Input: AI automation; LinkedIn and Twitter; 2 days

    Expected: JSON calendar includes topic, chosen platforms and calendar entries

    Command: python3 scripts/social_calendar.py 'AI automation' linkedin,twitter 2

    Observed: "topic": "AI automation", "brand": "AI automation", "platforms": [ "linkedin", "twitter" ], "duration_days": 2, "start_date": "2026-10-25", "end_date": "2026-10-27", "posting_schedule": { "linkedin": { "ideal": "3-5x/week", "minimum": "2x/week", "best_times": "Tue-Thu 8-10am, 12pm" }, "twitter": { "ideal": "3-5x/day", "minimum": "1x/day", "best_times": "9am, 12pm, 5pm" } }, "content_pillars": { "educational": { "name": "Educational", "description": "Teach your audience something valuable", "freq

Examples

  • Generate a social content calendar using the script.: command completed successfully

    Source: scripts/social_calendar.py main() usage/example

    Input: AI automation, linkedin,twitter, 2

    Expected: JSON content calendar with two entries

    Command: python3 scripts/social_calendar.py 'AI automation' linkedin,twitter 2

    Observed: flow": [ "1. Create a long-form piece about AI automation (blog post or YouTube video)", "2. Extract 5-7 key insights as individual social posts", "3. Turn each insight into a platform-specific format", "4. Create a carousel/thread from the full piece", "5. Film a 60s summary as a Reel/TikTok", "6. Pull quotes for image posts", "7. Create a poll or question from one insight", "8. Share behind-the-scenes of creating the content", "9. Reshare top-performing posts 2-4 weeks later", "10. Create a 'best of' compilation monthly" ] } }

Local or hosted: local

What the agent did

Generate a social media content calendar from a topic.

pwd && id -u && python3 --version && rg --files -g 'README*' -g 'pyproject.toml' -g 'package.json' -g 'requirements*.txt' -g 'AGENTS.md' -g '.github/**' | head -80
ls -la && find . -maxdepth 3 -type f | head -100 && sed -n '1,240p' README.md
cat requirements.txt && sed -n '1,220p' install.sh && for f in scripts/*.py skills/market-social/SKILL.md skills/market-report/SKILL.md; do echo "### $f"; sed -n '1,200p' "$f"; done
grep -nE 'usage|Usage|argparse|sys.argv|--output|--out|if __name__' scripts/*.py
sed -n '200,245p' scripts/social_calendar.py && sed -n '445,485p' scripts/analyze_page.py && sed -n '1,110p' .coldpass/*
bash ./install.sh > <guest-path> 2>&1; rc=$?; tail -30 <guest-path>; exit $rc
python3 scripts/social_calendar.py 'AI automation' linkedin,twitter 2 > <guest-path> && head -35 <guest-path>
mkdir -p .coldpass && python3 - <<'PY'
import json
p='<guest-path>'
argv=['python3','scripts/social_calendar.py','AI automation','linkedin,twitter','2']
probe={'kind':'cli','argv':argv,'cwd':'<guest-path>','expected_text':'"topic": "AI automation"'}
claim={'kind':'claim','claim':'Generate a 30-day social media content calendar.','source':'You generate a complete 30-day content calendar with platform-specific posts, hooks, hashtags, and a content repurposing strategy.','input':'AI automation; LinkedIn and Twitter; 2 days','expected':'JSON calendar includes topic, chosen platforms and calendar entries','probe_kind':'cli','argv':argv,'expected_text':probe['expected_text'],'cwd':probe['cwd']}
examples=[{'kind':'example','claim':'Generate a social content calendar using the script.','source':'scripts/social_calendar.py main() usage/example','input':'AI automation, linkedin,twitter, 2','expected':'JSON content calendar with two entries','argv':argv,'cwd':probe['cwd'],'expected_text':probe['expected_text']}]
cycles={'detected':False,'reason':'Repository entry points expose one-shot scripts and Claude Code skills; inspected scripts/social_calendar.py and README command table. No recurring scheduler or cycle trigger is provided.','checks':[]}
for name,obj in [('probe.json',probe),('claims.json',[claim]),('examples.json',examples),('cycles.json',cycles)]:
 with open(p+'/'+name,'w') as f: json.dump(obj,f,indent=2)
PY
<env-var>=<guest-path> python3 -I <guest-path> --validate --replay
grep -n -E '30-day|content calendar' README.md
python3 - <<'PY'
import json
p='<guest-path>'
x=json.load(open(p)); x[0]['source']='30-day social media content calendar'; json.dump(x,open(p,'w'),indent=2)
PY
<env-var>=<guest-path> python3 -I <guest-path> --validate --replay
python3 - <<'PY'
import json
p='<guest-path>'
r={'outcome':'working','fault_owner':None,'operation':'Generate a social media content calendar from a topic.','operation_scope':'Standalone Python social_calendar.py utility; Python 3.12.3 standard library, installer completed.','steps':['Read README and confirmed Python 3.12.3 is available.','Ran bash ./install.sh; it installed 14 skills, 5 agents, 4 scripts and 6 templates.','Ran python3 scripts/social_calendar.py "AI automation" linkedin,twitter 2 and observed a JSON calendar.','Validated and replayed probe, README claim, example and cycle evidence successfully.'],'deviations':['The README centers on Claude Code slash commands; no Claude Code executable/session was available, so exercised the included documented standalone social calendar script instead.'],'stuck_step':None,'main_blocker':None,'plain_failure':None,'suggested_fix':None}
json.dump(r,open(p,'w'),indent=2)
PY