Borrowing it
Nothing to install: this file belongs to swimmwatch/cloakbrowser-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/swimmwatch/cloakbrowser-mcp/main/.agents/skills/project-release/SKILL.mdgit clone --depth 1 https://github.com/swimmwatch/cloakbrowser-mcpWrote 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/swimmwatch/cloakbrowser-mcp/project-release)<a href="https://agentmods.dev/skills/swimmwatch/cloakbrowser-mcp/project-release"><img src="https://agentmods.dev/badge/skills/swimmwatch/cloakbrowser-mcp/project-release.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 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 174 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 MCP Rug Pull · line 121 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 162 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium Agent Snooping · line 135 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium MCP Rug Pull · line 161 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 163 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- low Tool Misuse · line 121 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00085 | $0.01875 |
| Opus 5 | $0.00043 | $0.00937 |
| Sonnet 5 | $0.00017 | $0.00375 |
| Haiku 4.5 | $0.00009 | $0.00187 |
Grade A, and why
project-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 8d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Release
Use this skill only for cloakbrowser-mcp release work. Require a confirmed
target version such as v1.2.8, and decide whether it is stable or prerelease
before preparing, publishing, or recovering a release. If the user has not
provided a target version, propose one from the unreleased changes and ask the
user through Prompt MCP to confirm it or choose a different tag before release
execution.
Release tags use Semantic Versioning 2.0.0 with the repository's v prefix,
for example v1.2.8 or v1.2.8-rc.1. The pinned specification URL is
https://semver.org/spec/v2.0.0.html.
Authorization And Interview
- Start or reopen a persistent workspace Prompt MCP interview with a stable ID
such as
release:vX.Y.Zafter inspecting the callable schemas. - Record target tag and stable/prerelease selection as separate material decisions. Treat only committed answers as confirmation.
- Release preparation, commit, push, release PR creation/update, merge, tag or GitHub Release creation, npm publication, Docker publication, MCP Registry publication, workflow rerun, and recovery mutations are separate authorization gates.
- Never infer publish authorization from version confirmation, preparation approval, merged code, or passing checks.
Choosing The Target Version
- If the user provides a target tag, validate it before changing files.
- If no target tag is provided, fetch tags and inspect changes since the previous release tag:
git fetch origin --tags --prune
git describe --tags --abbrev=0
git log --oneline <previous-tag>..HEAD
- Also inspect
[Unreleased]inCHANGELOG.md, merged PR titles, and Conventional Commit subjects when available. - Propose the next tag using Semantic Versioning 2.0.0:
MAJORfor backward-incompatible public API, CLI, MCP protocol, config, or artifact contract changes;MINORfor backward-compatible user-facing features;PATCHfor backward-compatible fixes, dependency updates, docs, CI, or packaging-only changes.
- Present the proposed tag and short rationale, then ask the user to confirm it
or choose another tag through Prompt MCP. Do not run
npm run version:applyuntil the tag is confirmed and release preparation is explicitly authorized.
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.
- 8d ago First seen · 184 lines · 85 tokens per session scan A 63d7e6c89b1a
project-release is a skill published in the GitHub repository swimmwatch/cloakbrowser-mcp (56 stars, last pushed 3d ago), licensed MIT. It adds 85 tokens to every session and 1,875 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 2026-08-30.
Other skills, from other repositories
chrome-releases
Queries Chrome commit, version, release, and milestone metadata. Use when finding the first landed Chrome version of a commit, checking channel releases across platforms, inspecting milestone schedules and branch refs, or checking version containment.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
omh-deploy-and-monitor
This is a Hermes-native deploy-and-monitor workflow skill.
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts) and an annotated tag. Verify, commit, tag. Stops at "committed and tagged locally" — no push, no publish. The release-and-publish skill picks up from here. Distilled…
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already…