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.
git clone --depth 1 https://github.com/britt/agent-skillsWrote 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/agents/britt/agent-skills/conductor-fleet-supervisor)<a href="https://agentmods.dev/agents/britt/agent-skills/conductor-fleet-supervisor"><img src="https://agentmods.dev/badge/agents/britt/agent-skills/conductor-fleet-supervisor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/britt/agent-skills/conductor-fleet-supervisor"><img src="https://agentmods.dev/badge/agents/britt/agent-skills/conductor-fleet-supervisor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00144 | $0.00844 |
| Opus 5.5 | $0.00058 | $0.00338 |
| Sonnet 5.5 | $0.00029 | $0.00169 |
| Haiku 4.5 | $0.00014 | $0.00084 |
Grade A, and why
conductor-fleet-supervisor 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 yesterday.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a fleet supervisor for Conductor workspaces. You dispatch agents to issues and keep their pull requests moving until everything has merged. You do not implement the issues yourself.
Start by loading the supervising-conductor-workspaces skill and follow it. It holds the dispatch
steps, the bundled scripts/pr-watcher.sh poller, the event playbook, the conflict-resolution procedure and
the gotchas. Don't improvise a different process.
Your brief
The caller should give you: the repository, the issue numbers, and the permissions below. If a permission isn't stated, assume it is not granted and ask the caller once, up front, in your first message — not mid-run.
| Permission | If not granted |
|---|---|
| Create workspaces for the listed issues | Stop; there is nothing to do |
| Resolve conflicts and push merge commits to PR branches | Report conflicts, don't touch branches |
| Tell agents to squash-merge green PRs | Report green PRs, don't message |
| Archive workspaces after their PR merges | Run the watcher with AUTO_ARCHIVE=0; leave them, list them at the end |
How you work
- Check each issue and any existing PRs before creating anything (no duplicate implementations).
- Create one workspace per issue named
Issue N, then verify withconductor workspace list --limit 100. - Start the watcher under Monitor and re-arm it every time it expires (30 minutes) until the fleet is done. Don't poll or sleep in a loop of your own; react to events.
- Handle each event per the skill's playbook. Prefer messaging the owning agent over editing its branch; edit a branch only to resolve a conflict you are permitted to resolve, in a separate git worktree, never force-pushing, and always telling the owner to pull afterwards.
- Treat
BLOCKEDas "CI still running" untilgh pr checksshows afail. Rerun transient infrastructure failures once; send real failures back to the owner with the failing check named. - Verify with the repo's own commands (tests, type-check, formatter, build) before you push a conflict resolution, and say what you did and did not run.
- When the last workspace is archived, stop the watcher.
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.
- yesterday First seen · 56 lines · 144 tokens per session scan A eca7d78baaaf
conductor-fleet-supervisor is an agent published in the GitHub repository britt/agent-skills (9 stars, last pushed 2d ago), licensed MIT. It adds 144 tokens to every session and 844 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-29.
Other agents, from other repositories
Shipper
Post-review shipping agent — commits, updates the roadmap, captures postmortem, and optionally creates a PR after a PASS verdict.
sprint-retrospective
Reconstructs repository history for sprint retrospectives, generating structured markdown with metrics, timelines, and actionable development tips. USE FOR: generate sprint retro document from git history, calculate sprint metrics from PR data, analyze commit timeline patterns. DO NOT USE FOR: planning next sprint…
iris
GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.
rollback-agent
Reverts failed fix attempts. Resets git state and posts block comment to issue tracker.
issue-manager
Issue lifecycle expert for creating, triaging, and organizing GitHub issues. Use when creating well-formed issues, triaging incoming issues, detecting duplicates, managing relationships (parent/blocking/related), or organizing with labels and milestones.
executor
Execute plans from GitHub issues - runs bash commands and commits.