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/implementgit 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 | $0.00016 | $0.03237 |
| Opus 5 | $0.00008 | $0.01618 |
| Sonnet 5 | $0.00003 | $0.00647 |
| Haiku 4.5 | $0.00002 | $0.00324 |
Grade A, and why
conductor:implement 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
!python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json implement parse-tracks
1.0 SYSTEM DIRECTIVE
You are an AI agent for the Conductor spec-driven development framework. Your task is to implement a track. Follow this protocol precisely.
CRITICAL: Validate every tool call. If any fails, halt immediately, announce the failure, and await instructions.
CLI Reference
# Status & archiving
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py implement update-status TRACK_ID STATUS
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py implement archive TRACK_ID
# Consolidated context (replaces multiple Reads)
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json tracks read-context TRACK_ID
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json implement git-snapshot [--diff-stat-only]
# Batch operations (replaces per-task calls)
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json implement batch-match-patterns --plan TRACK_ID
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json codereview filtered-diff [--base BRANCH] [--exclude PATH...]
# Task-level operations
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py tracks update-task TRACK_ID PHASE_IDX TASK_IDX STATUS
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json implement modified-files
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json implement parse-coverage --format FORMAT --path PATH
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json implement next-adr-number --path ADR_PATH
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json implement suggest-branch TRACK_ID
Fallback: If context injection fails, scan conductor/tracks/*/metadata.json directly.
1.0.1 WARM START DETECTION
PROTOCOL: Detect if implement was invoked directly from newTrack (context already loaded).
- Check arguments for
--warm-startflag (e.g.,args: "<TRACK_ID> --warm-start") - If
--warm-startis present:- Announce: "⚡ Warm start mode — skipping redundant setup (context carried over from newTrack)."
- Skip Section 1.1 (setup already verified during newTrack)
- Skip Section 2.1 (git branch was just created by newTrack)
- Proceed directly to Section 2.0 (track selection), then Section 2.2 (base branch detection)
- Set
WARM_START = truefor use in Section 3.0 Step 2
- If
--warm-startis NOT present: SetWARM_START = false, proceed normally to Section 1.1.
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 · 324 lines · 16 tokens per session scan A 68d70e5229b5
conductor:implement is a command published in the GitHub repository rbarcante/claude-conductor (56 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 3,237 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.