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.
git 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/campaign-auto)<a href="https://agentmods.dev/commands/001tmf/blatant-why/campaign-auto"><img src="https://agentmods.dev/badge/commands/001tmf/blatant-why/campaign-auto.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 | $0.00019 | $0.00929 |
| Opus 5 | $0.00010 | $0.00464 |
| Sonnet 5 | $0.00004 | $0.00186 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
by:campaign-auto scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/campaign-auto — Autonomous Campaign Pipeline
Run a complete design campaign end-to-end with minimal user interaction. Only stops for critical decisions (compute provider selection, cost approval). Everything else runs automatically with smart defaults.
Instructions
Step 0: Read config
MODEL_PROFILE=$(cat .by/config.json 2>/dev/null | grep -o '"model_profile"[[:space:]]*:[[:space:]]*"[^"]*"' | grep -o '"[^"]*"$' | tr -d '"' || echo "balanced")
If .by/config.json does not exist, run the by-session skill first-run setup before continuing.
Step 1: Parse target and auto-detect modality
Parse the user's input for target name/ID and any modality hints. Apply the modality detection table from the by-design-workflow skill. If ambiguous, default to VHH nanobody.
Step 2: Silent research (Agent tool — NO raw output)
Use the Agent tool to research the target. Do NOT call MCP tools directly.
Agent(
prompt="Research the protein target '[target]'. Call mcp__by-uniprot__uniprot_search, mcp__by-pdb__pdb_search, and mcp__by-sabdab__sabdab_search_by_antigen. Return ONLY: target name, organism, length, best PDB ID + resolution, known binder count. No JSON.",
description="Research [target]"
)
Step 3: Auto-configure campaign (smart defaults, no questions)
Use these defaults unless the user specified otherwise in their request:
- Modality: auto-detected from request text
- Epitope: structure-derived (automated)
- Tier: read from
.by/config.jsoncampaign_defaults.tier (or "standard") - Scaffolds: modality defaults
- Success criteria: balanced
Write campaign_context.json automatically. Do NOT ask AskUserQuestion.
Step 4: ONE confirmation — compute only
The ONLY question to ask the user:
AskUserQuestion(
header: "Compute",
question: "Ready to launch [N] designs on [provider]. Proceed?",
options: [
"Go" — Launch immediately,
"Change provider" — Switch compute (local/Tamarind/SSH),
"Adjust count" — Change number of designs
]
)
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.
- 7d ago First seen · 118 lines · 19 tokens per session scan A 27d5add3e3ac
by:campaign-auto is a command published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 21d ago), licensed MIT. It adds 19 tokens to every session and 929 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
read
Accepts: local PDF path, DOI, journal URL, or a pasted abstract with basic metadata.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.