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 skills add alexmond/alexmskills --skill conductorgit clone --depth 1 https://github.com/alexmond/alexmskillsWrote 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/skills/alexmond/alexmskills/conductor)<a href="https://agentmods.dev/skills/alexmond/alexmskills/conductor"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/conductor/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/skills/alexmond/alexmskills/conductor"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/conductor.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 | $0.00108 | $0.03227 |
| Opus 5.5 | $0.00043 | $0.01291 |
| Sonnet 5.5 | $0.00022 | $0.00645 |
| Haiku 4.5 | $0.00011 | $0.00323 |
Grade B, and why
conductor scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/conductor/learnings.md 2>/dev/null || echo "(none yet — this is a first run)" How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex: Read the client path before applying this workflow.
conductor
The conductor is the role the MAIN session adopts. Every other role is seated as a subagent and accumulates lessons in its own file; the conductor is seated nowhere, so its learnings exist and nothing loads them. That is the gap this skill closes: it is the loading mechanism, and the place new lessons land.
ticket-triage schedules ACROSS tickets. This skill governs what happens WITHIN a run:
is this lane doing what it was told, and what do I do when it is not.
First: read the accumulated learnings
cat .claude/conductor/learnings.md 2>/dev/null || echo "(none yet — this is a first run)"
cat .claude/roles/conductor.md 2>/dev/null | sed -n '/## Learnings/,$p'
Read both before acting. The installed plugin is a read-only cache; the repo's file is where this run's lessons go. Skipping this step is not hypothetical: a conductor re-made the "never edit a tree while a gate is running on it" mistake with a file that already said so, in the same repo, because nothing put it in front of them.
The measure problem — the failure that outranks all others
A lane will satisfy the done-when you wrote, not the one you meant. If the two differ, the lane is not at fault and telling it so wastes the round.
Measured, one repo, one epic: fourteen lanes, zero files moved. The work was retiring data files. Every brief said "nothing reads this file any more"; every lane achieved that, honestly. The owner's actual measure was the file has moved to its archive path — and a reader census satisfies the first while leaving the file exactly where it was.
The shape generalises past files: a done-when phrased as a PROPERTY ("it is no longer used", "the API is consistent", "the config is centralised") is satisfiable by argument. A done-when phrased as an OBSERVABLE ("this path no longer exists", "this query returns 0", "this command exits non-zero") is not.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +7 lines e33ea23d1794
- 1mo ago First seen · 240 lines · 108 tokens per session scan B 3c83a5b30846
conductor is a skill published in the GitHub repository alexmond/alexmskills (9 stars, last pushed 3d ago), licensed MIT. It adds 108 tokens to every session and 3,227 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-13.
Other skills, from other repositories
caveman-commit
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
git
Source-control safety for Git. Two rules apply whether or not you read the body. First, never commit, amend, push, tag, rebase, cherry-pick, revert, or reset --hard unless the user asked for that exact write in this session. An explicit request to create a new commit counts anywhere in the user's own task text, but it…
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
changelog
Auto-generate a changelog from git commits and sprint data. Internal and player-facing versions.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
install-skill
Install a community skill pack into this fork from a GitHub repo and ship it as an auto-merged PR.