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/codereviewgit 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 | $0.00017 | $0.02033 |
| Opus 5 | $0.00009 | $0.01017 |
| Sonnet 5 | $0.00003 | $0.00407 |
| Haiku 4.5 | $0.00002 | $0.00203 |
Grade A, and why
conductor:codeReview 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 3d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Usage
/conductor:codeReview master # Review against master
/conductor:codeReview develop # Review against develop
/conductor:codeReview # Will prompt for base branch
What This Command Does
- Generates filtered diff between current branch and base branch
- Analyzes changes across: Code Quality, Security, Test Coverage
- Generates report with findings organized by severity
1.0 SYSTEM DIRECTIVE
You are an AI agent specialized in code review. Analyze code across three dimensions: Code Quality, Security, and Test Coverage.
CRITICAL: Validate every tool call. If any fails, halt immediately, announce the failure, and await instructions.
1.1 SETUP CHECK
Verify existence of context files for standards-aware review:
conductor/product-guidelines.md— product style and messagingconductor/tech-stack.md— technology choicesconductor/workflow.md— TDD requirements, coverage thresholdsconductor/code_styleguides/— code style guides
If missing, announce warning and continue with generic standards.
2.0 BRANCH SELECTION AND DIFF GENERATION
2.1 Select Base Branch
- Check argument: Parse
{{args}}for base branch name. - If no argument: Prompt via AskUserQuestion with options: master / develop / main.
- Store selection as
BASE_BRANCH.
2.2 Generate Filtered Diff via CLI
Execute a single call that handles fetch, diff, stats, and language detection:
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json codereview filtered-diff --base <BASE_BRANCH>
The response includes:
data.base_branch— validated base branchdata.stats—files_changed,lines_added,lines_removed,truncated,max_linesdata.language_breakdown— per-language file counts and line changesdata.file_stats— per-file breakdown with language detectiondata.diff_content— full filtered diff (size-capped)
Handle errors:
- If base branch not found: "Branch
origin/<BASE_BRANCH>not found." — re-prompt. - If diff is empty: "No changes found. Your branch appears up-to-date." — halt.
- If CLI fails: Fall back to manual
git fetch origin && git diff origin/<BASE_BRANCH>...HEAD.
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.
- 3d ago First seen · 276 lines · 17 tokens per session scan A d0063ca2395c
conductor:codeReview is a command published in the GitHub repository rbarcante/claude-conductor (56 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 2,033 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
git
Git operations with intelligent commit messages and workflow optimization.
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.