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 OutlineDriven/outline-driven-development --skill cut-new-release-candidategit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/cut-new-release-candidate)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/cut-new-release-candidate"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cut-new-release-candidate/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/outlinedriven/outline-driven-development/cut-new-release-candidate"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cut-new-release-candidate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Data Exfiltration · line 109 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00044 | $0.02017 |
| Opus 5 | $0.00022 | $0.01009 |
| Sonnet 5 | $0.00009 | $0.00403 |
| Haiku 4.5 | $0.00004 | $0.00202 |
Grade A, and why
cut-new-release-candidate scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If `INTERNAL_REPO` or `NOTIFICATION_TOKEN` is unset, stop and ask before running. Required tools: `git`, an authenticated `gh`, `jq`, and `curl`. Run all git and gh operations inside the release repo. How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cut new release candidate
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks to cut, trigger, or start a release candidate for a release branch. |
| Authority | Remote: dispatches the release workflow on the named branch and posts one status notification; requires explicit human invocation. Preview the target and consequence before each remote mutation; mutate only the one workflow dispatch on the branch the user named and the one status notification. |
| Side effect | Runs the configured release workflow on the release branch, obtains its run URL, and posts one status notification. Nothing else changes. |
| Done | The workflow dispatch exits zero, the run query returns a non-null run URL, and the status notification is posted. |
Inputs
Required from the user:
- The release branch name. Strip a leading
origin/before validating. - Optionally, a notification destination (channel, thread, or recipient). Ask before posting if no destination was supplied.
The operator environment must supply these values before any step:
INTERNAL_REPO: theowner/repocontaining the release branches and workflow.REPO_DIR: the absolute path to its local checkout.RC_WORKFLOW_NAME: the release-candidate workflow name. Default:Cut New Release Candidate.RELEASE_CHANNELS: space-separated channel names. Default:preview stable.RELEASE_BRANCH_PREFIX: per-channel branch prefix template, with{channel}replaced by each channel name. Default:{channel}_release/.NOTIFICATION_TOKEN: a token for the notification service with write scope. Read it only from the environment; never hardcode or commit it.NOTIFICATION_ENDPOINT: the API endpoint for posting the status notification.
If INTERNAL_REPO or NOTIFICATION_TOKEN is unset, stop and ask before running. Required tools: git, an authenticated gh, jq, and curl. Run all git and gh operations inside the release repo.
Procedure
- Validate the branch at the trust boundary: set the requested branch, strip the
origin/prefix, and reject any branch that does not start with a configured channel prefix:
What ships with it
1 file 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.
- 2d ago Changed · +17 lines · -27 tokens per session 44ccc814afda
- 5d ago First seen · 114 lines · 71 tokens per session scan A 32973d490c68
cut-new-release-candidate is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 44 tokens to every session and 2,017 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
releasepr
Adopt, configure, run, or troubleshoot compozy/releasepr in a consuming repository, including Actions, beta/stable/legacy plans, notes, dry-runs, and publication. Excludes pr-release internals and general versioning advice.
push-ci
Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
aiox-devops
GitHub Repository Manager & DevOps Specialist (Gage). Use for repository operations, version management, CI/CD, quality gates, and GitHub push operations. ONLY agent authorized...
tfx-ship
A release workflow for publishing triflux versions through GitHub Releases, the npm package registry, and the Claude Code marketplace. It also supports version changes, dry runs, skipped tests, and no-publish runs.
aws-ci-cd-release-engineer
Review AWS CI/CD and release safety across CodePipeline, CodeBuild, CodeDeploy, GitHub Actions, GitLab, artifact provenance, deployment gates, approvals, tests, progressive delivery, rollback, change correlation, and incident-prevention recommendations. Use when AWS releases or pipelines can affect production…