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/001tmf/blatant-why/resumegit clone --depth 1 https://github.com/001TMF/blatant-whyWrote 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/001tmf/blatant-why/resume)<a href="https://agentmods.dev/commands/001tmf/blatant-why/resume"><img src="https://agentmods.dev/badge/commands/001tmf/blatant-why/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 5.1 | $0.00012 | $0.01409 |
| Opus 5 | $0.00006 | $0.00705 |
| Sonnet 5 | $0.00002 | $0.00282 |
| Haiku 4.5 | $0.00001 | $0.00141 |
Grade A, and why
by:resume scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/resume -- Resume Campaign from Last Checkpoint
Resume an interrupted or failed campaign from its most recent checkpoint.
Instructions
This command reads checkpoint files to determine exactly where the campaign stopped, then dispatches the appropriate agent to continue from that point.
Step 1: Find the campaign directory
CAMPAIGN_DIR=$(cat .by/active_campaign 2>/dev/null || echo "")
If no active campaign is set, scan .by/campaigns/ for the most recently
modified campaign directory. If multiple campaigns exist, list them and ask the
user which one to resume.
Step 2: Read checkpoint files
Scan $CAMPAIGN_DIR/checkpoints/ for checkpoint files. They are named by phase
with numeric prefix for ordering:
checkpoints/
00_draft.json -- campaign created
01_configured.json -- plan approved, parameters set
02_designing.json -- jobs submitted (includes job_ids)
03_design_complete.json -- results received
04_screening.json -- screening started
05_screening_complete.json -- scores computed
06_ranking.json -- composite scores computed
07_complete.json -- campaign done
Identify the latest checkpoint file (highest numeric prefix). This is the resume point.
Step 3: Read checkpoint contents
Each checkpoint file contains:
{
"phase": "designing",
"timestamp": "2026-03-24T15:00:00Z",
"campaign_id": "pd-l1-20260324-150000",
"completed_actions": ["research", "plan_approval", "job_submission"],
"pending_actions": ["monitor_jobs", "collect_results"],
"job_ids": ["by_boltzgen_abc123"],
"partial_results": {
"designs_received": 5,
"designs_expected": 20,
"designs_scored": 3
},
"next_action": "poll_job_status",
"agent_to_dispatch": "by-design",
"resume_context": "Jobs submitted to Tamarind. 5/20 designs returned before interruption."
}
Step 4: Build resume plan
Present the resume plan to the user:
------------------------------------------------------
BY > RESUME CAMPAIGN
------------------------------------------------------
**Campaign:** {campaign_id}
**Last checkpoint:** {phase} ({timestamp})
**Interrupted at:** {resume_context}
**Completed phases:**
{for each completed_action: " * {action}"}
**Resume action:** {next_action}
**Agent:** {agent_to_dispatch}
**Partial results (if any):**
- Designs received: {designs_received}/{designs_expected}
- Designs scored: {designs_scored}
------------------------------------------------------
> Type "go" to resume, or describe adjustments
------------------------------------------------------
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.
- 6d ago First seen · 173 lines · 12 tokens per session scan A 7f216f14b71a
by:resume is a command published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 20d ago), licensed MIT. It adds 12 tokens to every session and 1,409 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
graphiti-health
Display unified real-time health status for Neo4j Aura and Graphiti services.
scaffold-fastmcp-v2
Scaffold a new FastMCP server with standard Life Sciences project structure following ADR-001 patterns.
graphiti-aura-stats
Generate production graph statistics for Neo4j Aura analytics and capacity planning.
graphiti-docker-stats
Generate development environment statistics for Docker Neo4j namespace management.
scaffold-fastmcp
Scaffold a new FastMCP server with standard Life Sciences project structure following ADR-001 patterns.
graphiti-verify
Run Day 1 verification sequence to confirm environment is working.