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/aaronbassett/agent-foundry/councilgit clone --depth 1 https://github.com/aaronbassett/agent-foundryWrote 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/aaronbassett/agent-foundry/council)<a href="https://agentmods.dev/commands/aaronbassett/agent-foundry/council"><img src="https://agentmods.dev/badge/commands/aaronbassett/agent-foundry/council.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 | $0.00041 | $0.00811 |
| Opus 5 | $0.00020 | $0.00405 |
| Sonnet 5 | $0.00008 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
council 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/decision-making:council
When to use
The question is ambiguous, value-laden, or multi-stakeholder and no single perspective can resolve it cleanly. Use when framing matters as much as conclusions. Useful when you suspect the "right answer" depends on whose pain point you're solving.
Cost tier
Medium. 4-6 parallel Lens subagents (sonnet model), one round. See references/cost-tiers.md.
Input
The question + relevant context.
Optional: --lenses=<comma-separated list> to specify lenses explicitly. Useful for recurring decision types where consistency across runs matters.
Workflow
-
Determine lenses — if
--lenses=<list>is provided, use exactly those lenses. Otherwise, the main thread identifies 4-6 distinct lenses relevant to the question and states its selection (with a short justification for each lens) in the Reasoning section of the output. Example lenses for a technical decision:- The ops engineer who'll be paged at 3am
- The new hire reading this in 6 months
- The security reviewer
- The staff eng optimizing for system coherence
- The PM shipping Friday
- The principal eng thinking 2 years out
-
Spawn one Lens subagent per lens in parallel — use the Agent tool with
subagent_type: lens. Each subagent is given its assigned lens + a short description of what that lens cares about + the question + relevant context. Include this exact prompt template:You inhabit this perspective: [LENS NAME] What this perspective cares about: [WHAT THE LENS CARES ABOUT] The question: [QUESTION] Context: [RELEVANT CONTEXT] Write a short position statement (~150 words) from your assigned perspective alone. Do not frame it as "from the X perspective..." — write as if you ARE this perspective and it is the only one that matters. Do not meta-comment. Do not try to be balanced. Inhabit the lens. -
Collect positions — gather all parallel responses. Do not share them between subagents (the
Lensagent definition already enforces non-cross-contamination, but the main thread should also avoid accidentally passing one lens's output to another).
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 · 67 lines · 41 tokens per session scan A 1f4cb8a78e5d
council is a command published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 21d ago), licensed MIT. It adds 41 tokens to every session and 811 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 commands, from other repositories
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.