synerise-design: Skill for Claude Code

.claude/skills/ds-release/SKILL.md

ds-release is a skill for Claude Code from Synerise/synerise-design. It costs 71 tokens per session (7,130 once invoked), scanned A, original, MIT.

An end-to-end release workflow for a package set managed with Lerna, a JavaScript package and monorepo tool. It publishes bumped packages, creates changelogs and release records, notifies a Microsoft Teams channel, and can prepare upgrade changes in consumer repositories.

In plain words
What is it for?
Use it to publish a release, generate a changelog from GitLab merge requests, create Jira and GitLab release records, notify Teams, and optionally open consumer merge requests.
Why use it?
It brings package publishing, release tracking, communication, and optional downstream updates into one repeatable process.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code.

This is Synerise/synerise-design's own configuration. It tells Claude Code how to work on synerise-design itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything synerise-design configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is source ~/.zshrc 2>/dev/null && bash scripts/notify-teams.sh \.

Reuse

Borrowing it

Nothing to install: this file belongs to Synerise/synerise-design. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Synerise/synerise-design/master/.claude/skills/ds-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Synerise/synerise-design

Made for: Claude Code.

Wrote 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.

agentmods badge for ds-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/synerise/synerise-design/ds-release/github.svg)](https://agentmods.dev/skills/synerise/synerise-design/ds-release)
Your own site
<a href="https://agentmods.dev/skills/synerise/synerise-design/ds-release"><img src="https://agentmods.dev/badge/skills/synerise/synerise-design/ds-release/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.

agentmods 80×15 button for ds-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/synerise/synerise-design/ds-release"><img src="https://agentmods.dev/badge/skills/synerise/synerise-design/ds-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,130 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, 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 Privilege Escalation · line 11
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 12
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 379
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Rogue Agent · line 3
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 164
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium MCP Rug Pull · line 361
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.07130
Opus 5 $0.00036 $0.03565
Sonnet 5 $0.00014 $0.01426
Haiku 4.5 $0.00007 $0.00713

Measured 4d ago against content hash a9899c62be08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ds-release 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 4d 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.

.claude/skills/ds-release/SKILL.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prerequisites

The following environment variables must be set:

  • GITLAB_TOKEN — GitLab personal access token (scope: read_api) for gitlab.synerise.com — used for all reads
  • GITLAB_WRITE_TOKEN — GitLab personal access token (scope: api, Developer role on the project) for gitlab.synerise.com — used for write actions: creating the GitLab release (Step 10) and creating the consumer MRs (Phase 3). read_api cannot create releases or MRs. If this variable is not set, skip those writes and tell the user.
  • JIRA_EMAIL — Atlassian account email
  • JIRA_TOKEN — Atlassian API token
  • TEAMS_RELEASES_WEBHOOK — Power Automate incoming webhook for the Teams releases-changelog channel (Step 11). Also exists as a CI variable; for local skill runs export it in your shell profile too. If unset, scripts/notify-teams.sh no-ops and the rest of the run still completes.
  • GITLAB_PIPELINE_TRIGGER_TOKEN — GitLab pipeline trigger token (glptt-…) for the puib build trigger in Phase 3 (Step 15). Distinct from the PATs above. If unset, the puib pipeline trigger is skipped (ask the user for it).
  • GITLAB_PERSONAL_TOKEN — the user's personal api-scoped PAT (Developer+ on the consumer repos). Required to create the consumer MRs in Phase 3 (Step 15); the project-bot tokens above can't write cross-project. Depending on where it is exported, it may only be present after sourcing the shell profile (see the note below).

Important: These variables may not be available in Claude Code's shell by default. Before any API call, source the user's shell profile first (e.g. source ~/.zshrc 2>/dev/null — adjust to whatever profile file the user keeps these in). Prepend this to every Bash command that uses these variables.

The GitLab project ID for Frontend/synerise-design is 1171. The Jira project key is STOR. The Jira base URL is https://hgintelligence.atlassian.net.

Registry: DS packages are published to public npm by CI, but the consumer repos install from the internal Nexus registry https://nexus.snrinternal.com/repository/npm-release — so the "is it published yet?" gate in Phase 3 must query Nexus (it proxies npm and can lag slightly behind the publish).

Consumer repos (for the optional Phase 3):

Repo GitLab project ID Default branch
portal-ui-bridge (puib) Frontend/portal-ui-bridge 1098 master
portal-next Frontend/portal-next 1244 master

Locate each repo's local clone on the machine before operating on it — clones can live anywhere and under any directory name, so don't assume a fixed path. Confirm the clone's origin remote matches the GitLab project above (git -C <clone> remote get-url origin). Ask the user for the path if it can't be found.

Read the full file on GitHub · 422 lines

Changes

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.

  1. 4d ago First seen · 422 lines · 71 tokens per session scan A a9899c62be08

Subscribe to this mod's changes

ds-release is a skill published in the GitHub repository Synerise/synerise-design (96 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 7,130 once invoked, about $0.0004 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 2026-09-04.