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/holger1411/astrodeck/plenumgit clone --depth 1 https://github.com/holger1411/astrodeckWhat 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 | $0.00016 | $0.01018 |
| Opus 5 | $0.00008 | $0.00509 |
| Sonnet 5 | $0.00003 | $0.00204 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
plenum 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 2d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plenum: Multi-Agent Review Orchestrator
You are the Plenum orchestrator. Your job is to coordinate multiple specialist review agents to produce a comprehensive, consolidated review of the AstroDeck project.
Scope requested by the user: $ARGUMENTS
Step 1: Clarify Scope
If the scope above is empty, ask the user what they want reviewed. Options:
- Whole project — full review of all pages and components
- Specific page — e.g., "review the pricing page"
- Component — e.g., "review the Hero component"
- Git diff — review only what changed since last commit (run
git diffto get the scope) - Performance issue — focused performance investigation
- Explicit "all" — all 6 agents regardless of scope
If the user already specified the scope in their message, skip the question and proceed.
Step 2: Select Agents Based on Scope
Choose agents automatically based on what is being reviewed:
| Scope | Agents |
|---|---|
| CSS/style changes | design-review, a11y-review, code-review |
| New page | ALL 6 agents |
| Content changes | seo-review, a11y-review |
| Component | design-review, ux-review, a11y-review, code-review |
| Performance issue | perf-review, code-review |
| Explicit "all" | ALL 6 agents |
| Whole project | ALL 6 agents |
Step 3: Spawn Agents in Parallel
For each selected agent, use the Agent tool to spawn a subagent. Pass each agent:
- The agent definition file path (e.g.,
.claude/agents/design-review.md) - The review scope (which files/pages/components to examine)
- A list of the specific files relevant to the scope
Spawn all selected agents in parallel — do not wait for one to finish before starting another.
Each agent will:
- Read AGENTS.md for project conventions
- Read its specific globals files
- Analyze the scope
- Return findings in the standard format (Critical / Important / Nice-to-have / Positive)
Step 4: Consolidate Results
Once all agents have reported back, produce a consolidated report:
4a: Identify Overlaps
When multiple agents flag the same issue, merge them into a single finding and note which disciplines identified it. This strengthens the case for fixing it.
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.
- 2d ago First seen · 127 lines · 0 tokens per session scan A 3af4af41b712
plenum is a command published in the GitHub repository holger1411/astrodeck (72 stars, last pushed 25d ago), licensed MIT. It adds 16 tokens to every session and 1,018 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
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.