Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/indranilbanerjee/contentforge/resumegit clone --depth 1 https://github.com/indranilbanerjee/contentforgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/indranilbanerjee/contentforge/resume)<a href="https://agentmods.dev/commands/indranilbanerjee/contentforge/resume"><img src="https://agentmods.dev/badge/commands/indranilbanerjee/contentforge/resume.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00012 | $0.01960 |
| Opus 5 | $0.00006 | $0.00980 |
| Sonnet 5 | $0.00002 | $0.00392 |
| Haiku 4.5 | $0.00001 | $0.00196 |
Grade A, and why
resume scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- resume — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume Interrupted Pipeline
Pick up a /contentforge:create-content run that stopped before Phase 8 finished — instead of restarting from scratch, load the run manifest and continue from the next phase (or the pending rework target).
Trigger
User runs /contentforge:resume (with optional run-id argument). Also surface this command in any error message when a pipeline run terminates abnormally.
What this fixes
ContentForge's 10-phase pipeline is long-running. If the underlying agent session terminates partway through (context-window exhaustion, network blip, user cancels, machine sleeps), the in-memory Phase 1-N outputs disappear. Every phase that passes its quality gate writes its output to ~/.claude-marketing/{brand-slug}/runs/{run_id}/ via scripts/checkpoint-manager.py, so a fresh session can reload those artifacts and skip the phases that already completed.
Process
Step 0: Cross-session checkpoint download (Cowork only)
Before listing local runs, check if we're in Cowork+Drive mode — if so, the user might be resuming from a DIFFERENT Cowork session (different sandbox), and the local FS has no record of the run. Pull the run's checkpoint state from Drive first.
python ${CLAUDE_PLUGIN_ROOT}/scripts/drive-sync-state.py --action read-config
If configured: false OR environment != "cowork-sandbox", skip to Step 1 (local-mode flow).
If configured: true AND a Drive MCP is available:
- Use the Drive MCP to list contents of
{drive_root_folder_name}/_runs/ - For each
<run_id>subfolder, check if it has phase artifacts (phase-*.md,_manifest.json,_sync-pending.json) - Identify in-progress runs (manifest exists but
phase_artifactsdoesn't includephase 8— i.e., output-manager hasn't completed) - For each in-progress run that doesn't yet exist locally at
~/.claude-marketing/{brand-slug}/runs/{run_id}/:- Use the Drive MCP to download every file from
{drive_root}/_runs/{run_id}/into the local sandbox path - This restores the run's full checkpoint history so Step 2 below can load artifacts normally
- Use the Drive MCP to download every file from
- Tell the user: "Pulled {N} run(s) from Drive for resume eligibility: {run_id list}"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 128 lines · 12 tokens per session scan A 12c63666ed5d
resume is a command published in the GitHub repository indranilbanerjee/contentforge (26 stars, last pushed 18d ago), licensed MIT. It adds 12 tokens to every session and 1,960 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
engagement
Run a marketing engagement using the 12-Part methodology. Subcommands: start, next, status, validate, re-run-decision, update-back, lif-show, file-tree, list-engagements, four-core, growth-plan, yearly-planner, loop.
resume
Resume a long-running DMP workflow (engagement / campaign-plan / content-engine / seo-audit / competitor-analysis / campaign-audit / launch-campaign) that was interrupted partway through.
execute-action
Actually fire a campaign-audit / launch-campaign action against its real API (vs returning a manifest). Reads credentials from env vars (no OAuth flow). Read ops auto-execute with --execute; write ops require --confirm. Logs every execution to the audit trail.
output-folder
Print + open the user-visible DMP output folder for a brand (/Documents/DigitalMarketingPro/{brand}/). Direct answer to "where did my engagement deliverables save?".
check
Run the unified pre-publish quality gate on marketing content (hallucination + brand voice + structure + claims). Use before publishing any marketing copy.
doctor
Per-action readiness diagnostic. Shows which campaign-audit and launch-campaign actions are live (manifest-ready) vs blocked (stub-unconfigured) in the current environment, with one-step setup hints for the blocked ones. Now includes model-registry freshness + Cowork+Drive routing status.