Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/product-on-purpose/pm-skillsnpx agentmods add skills/product-on-purpose/pm-skills/utility-pm-release-conductorWrote 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/product-on-purpose/pm-skills/utility-pm-release-conductor)<a href="https://agentmods.dev/skills/product-on-purpose/pm-skills/utility-pm-release-conductor"><img src="https://agentmods.dev/badge/skills/product-on-purpose/pm-skills/utility-pm-release-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/product-on-purpose/pm-skills/utility-pm-release-conductor"><img src="https://agentmods.dev/badge/skills/product-on-purpose/pm-skills/utility-pm-release-conductor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 14 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00090 | $0.01598 |
| Opus 5 | $0.00045 | $0.00799 |
| Sonnet 5 | $0.00018 | $0.00320 |
| Haiku 4.5 | $0.00009 | $0.00160 |
Grade A, and why
utility-pm-release-conductor 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Release Conductor (Dispatch Skill)
Cross-client dispatch wrapper for the pm-release-conductor sub-agent. Detects runtime; dispatches to the native sub-agent on Claude Code; reads agents/pm-release-conductor.md and inlines chain composition on non-Claude clients via "reference + execute inline" pattern.
Status summary (v2.16.0): PRODUCTION on Claude Code (native sub-agent path). DRY-RUN VALIDATED on Codex CLI 2026-05-17 per
gate-test-results_2026-05-17_codex.md; LIVE release on Codex CLI is NOT independently exercised, so use with caution and run--dry-runfirst as a rehearsal. EXPERIMENTAL on Cursor / Windsurf / Copilot CLI / Gemini CLI (UNTESTED at v2.16.0 ship).See Sub-Agent Compatibility Matrix for the canonical safe-usage matrix + what-was-validated detail + v2.17 expansion plan. For live release on a non-Claude client, ideally re-run the harness at
maintainer-gate-testing-codex.mdon that specific client first.
When to Use
- You are running a pm-skills release on a non-Claude client (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI)
- You want the same 6-gate discipline that pm-release-conductor enforces on Claude Code, with auditor + curator behaviors inlined at the relevant gates
- You explicitly want skill-invocation semantics over sub-agent semantics on Claude Code (rare; the native sub-agent is preferred on Claude Code)
When NOT to Use
- You only need to review a PM artifact -> use
utility-pm-critic - You only need a governance audit (not a release) -> use
utility-pm-skill-auditor - You only need a CHANGELOG draft (not a release) -> use
utility-pm-changelog-curator - You want to perform release operations WITHOUT explicit gate confirmation -> the conductor refuses bypass; manual release outside the conductor is the right path
What ships with it
4 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.
- 9d ago First seen · 80 lines · 90 tokens per session scan A aff2c86c2e7e
utility-pm-release-conductor is a skill published in the GitHub repository product-on-purpose/pm-skills (663 stars, last pushed yesterday), licensed Apache-2.0. It adds 90 tokens to every session and 1,598 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
ds-ship
Ship orchestrator — classify the project, pick a mode (improve/release/launch/maintain), delegate only the skills the project's signals justify, consolidate findings, produce an audit report. Use for an end-to-end audit or ship pipeline across multiple skills.
drupal-mr
Create or list merge requests for drupal.org projects via git.drupalcode.org. Invoke when user wants to create a merge request for a drupal.org issue, says "create a drupal.org MR", "set up a merge request for issue", or uses /drupal-mr. Has side effects: clones repos to /.cache/drupal-contrib/ and pushes to…
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
operating-github-cli
Default GitHub skill for the action agent. Use githubcli for any GitHub request — create/list/view/close issues and PRs, assign, labels, repos, releases, checks, github.com/owner/repo URLs, or gh api. Prefer over shellrun/!gh. Run these with githubcli in the current agent turn.
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.