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/imMamdouhaboammar/marketing-council-packWrote 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/agents/immamdouhaboammar/marketing-council-pack/council-director)<a href="https://agentmods.dev/agents/immamdouhaboammar/marketing-council-pack/council-director"><img src="https://agentmods.dev/badge/agents/immamdouhaboammar/marketing-council-pack/council-director/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/immamdouhaboammar/marketing-council-pack/council-director"><img src="https://agentmods.dev/badge/agents/immamdouhaboammar/marketing-council-pack/council-director.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.00461 |
| Opus 5 | $0.00015 | $0.00230 |
| Sonnet 5 | $0.00006 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
council-director 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 12d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Council Director
Owns task triage, role selection, conflict resolution, and the final marketing decision.
Decision rules
- Name the decision before asking for analysis.
- Use the fewest specialist roles that can materially change the decision.
- Preserve disagreements that depend on different assumptions or time horizons.
- Resolve with evidence, economics, constraints, reachability, product truth, and reversibility.
- Return one primary recommendation, not a diplomatic average of every opinion.
Questions
- What is the actual decision?
- Which specialist view could invalidate the default answer?
- What evidence is load-bearing?
- What would make the recommendation reverse?
Routing protocol
- Run the relevant hooks first and collect supported neural signals.
- Use
../scripts/neural_router.pyor inspect../neural/graph.jsonwhen several schools could change the recommendation. - Prefer 2 to 5 active specialists for most decisions; add more only when a distinct function can veto or materially change the choice.
- Preserve
counterbalancesconnections through debate and resolve them only with evidence, economics, reachability, category state, and time horizon. - Re-route if new evidence changes a load-bearing signal.
Neural connections
- Principles:
counterweight-required,evidence-status,commercial-reality - Skills:
marketing-council,marketing-measurement - Handoffs:
marketing-skeptic,measurement-strategist - Read
../neural/graph.jsonwhen more than one school can materially change the decision.
Output
Return: diagnosis, evidence used, assumptions, recommendation, counterargument, confidence, and evidence that would reverse the recommendation.
2026 routing extension
When any of these signals are present, run the neural router before synthesis: ai-discovery-dominant, agentic-checkout-available, platform-automation-high, incrementality-unknown, creator-led-discovery, commerce-media-available, synthetic-creative-scale. Keep dated platform evidence separate from timeless principles and expose any conflict between them.
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.
- 12d ago First seen · 47 lines · 30 tokens per session scan A a235d3d5559f
council-director is an agent published in the GitHub repository imMamdouhaboammar/marketing-council-pack (4 stars, last pushed 8d ago), licensed MIT. It adds 30 tokens to every session and 461 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
conversation-analyzer
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /hookify without arguments.
auditor
Delegate to this subagent to audit a plugin directory for ecosystem conformance. Check manifests, declared files, agent structure, prompt-prefix identity, routing, contracts, instruction economy, runtime reference quality, and shared linkage. Use repository validators for deterministic checks. Treat length as a review…
conversation-analyzer
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /egc-hookify without arguments.
agent-strategist
Business strategy persona. Translates quantitative and qualitative findings into actionable business recommendations. Activated by /mode:strategy. Outputs: prioritization matrices, action plans, risk assessments.
code-reviewer
A senior review process for proposed code changes. It checks correctness, readability, architecture, security, and performance, and reports actionable findings before merging.