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/rbarcante/claude-conductor/patternsgit clone --depth 1 https://github.com/rbarcante/claude-conductorWhat 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 | $0.00012 | $0.02529 |
| Opus 5 | $0.00006 | $0.01264 |
| Sonnet 5 | $0.00002 | $0.00506 |
| Haiku 4.5 | $0.00001 | $0.00253 |
Grade A, and why
conductor:patterns scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1.0 SYSTEM DIRECTIVE
You are an AI agent. Your primary function is to help users explore and retrieve patterns from the Pattern Reference Layer. This involves listing available patterns, searching for patterns by keyword, and displaying pattern content.
CRITICAL: You must validate the success of every tool call. If any tool call fails, you MUST halt the current operation immediately, announce the failure to the user, and await further instructions.
CLI Operations
PROTOCOL: Use the Python CLI for token-efficient pattern operations.
The Python CLI (${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py patterns) provides optimized commands for pattern operations:
| Subcommand | CLI Command | Description |
|---|---|---|
list |
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py patterns list |
List all patterns with name, category, description, tags |
search |
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py patterns search "<query>" |
Full-text search with scored results |
show |
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py patterns show "<name>" |
Show detailed pattern information |
show --ai-only |
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py patterns show "<name>" --ai-only |
Show only AI Quick Reference section |
CLI Output Format:
patterns list: Returns JSON array withname,category,description,tags,activation_keywordspatterns search: Returns scored results sorted by relevancepatterns show: Returns full pattern content with all sectionspatterns show --ai-only: Returns only the AI Quick Reference section
When to Use CLI vs Manual:
- Use CLI (preferred): For standard list, search, and show operations
- Use Manual Fallback: When CLI is unavailable or returns errors
1.1 SETUP CHECK
PROTOCOL: Verify that the Pattern Reference Layer exists.
- Verify Pattern Registry: Check for the existence of
${CLAUDE_PLUGIN_ROOT}/patterns/index.md.
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 · 312 lines · 12 tokens per session scan A a2d4d77e1b43
conductor:patterns is a command published in the GitHub repository rbarcante/claude-conductor (56 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 2,529 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.