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 agentmods add skills/physics91/openrouter-mcp/deploynpx skills add physics91/openrouter-mcp --skill deploygit clone --depth 1 https://github.com/physics91/openrouter-mcpWhat 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 | $0.00025 | $0.00676 |
| Opus 5 | $0.00013 | $0.00338 |
| Sonnet 5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
deploy 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 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.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy Skill
Target: npm registry (@physics91/openrouter-mcp). Always manual, intentional.
Execution Baseline
- Prefer
python3for Python commands. - If
python3is unavailable butpythonexists, usepythonas fallback. - If pip installation is blocked by externally-managed environment (PEP 668), run quality/test gates in local
.venv. deployowns release hygiene as well as publish commands. Do not treat metadata checks as optional.
Pre-flight Checklist
Run in order. Stop at first failure:
- Version: Confirm
versioninpackage.jsonis the intended release (semver). - Build gate: Run
buildskill in check mode.ruff,black, andisortmust all pass. - Assurance gate: Run
python3 run_tests.py assurance -vthrough thetestskill. - Metadata sanity: Check
package.jsonfields:authorhomepagerepositorybugs
- Placeholder scan: Run:
Release only when the results are understood and intentional.rg -n "yourusername|yourproject.com|your-domain-here|Your Name" package.json CHANGELOG.md README.md SECURITY.md docs - Release notes and links: Verify
CHANGELOG.mdversion section and comparison links. - Package contents: Run:
Confirm the package includes the expected files and excludes junk.npm pack --dry-run - Install-doc consistency: Spot-check scoped package naming in
README.mdanddocs/INSTALLATION.md. - npm auth: Run
npm whoami. If not logged in, runnpm login. - Manual confirmation: Confirm with the user before publish.
Publish
npm publish --access public
Post-publish
- Tag the release in git:
git tag v<version> git push origin v<version> - Verify registry version:
npm info @physics91/openrouter-mcp version - If the package page or docs are part of the release checklist, verify them after publish.
Package Contents
Defined by files field in package.json:
bin/, src/, requirements.txt, requirements-dev.txt, pytest.ini, docs/, README.md, CONTRIBUTING.md, LICENSE
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 First seen · 74 lines · 25 tokens per session scan A 8b538b24d711
deploy is a skill published in the GitHub repository physics91/openrouter-mcp (9 stars, last pushed 20d ago), licensed MIT. It adds 25 tokens to every session and 676 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
release-notes
Draft concise release notes.
greptimedb-release
Runbook for publishing a new GreptimeDB version (tag + GitHub release + docs release-note PR) on the upstream GreptimeTeam/greptimedb repo. Use when asked to "release" / "publish" a GreptimeDB version (e.g. v1.1.0, v1.0.3).
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…
store-update
在 CCX Desktop 发布后下载 Store MSIX 并生成发布公告。用户提到 Store 上架、MSIX、从 GitHub Release 下载 store.msix、发布后同步 Windows Store、从 release 填写商店更新内容时必须使用此技能。该技能会下载最新 GitHub Release 的 amd64/arm64 MSIX，校验 sha256，从 Release body 生成 Store listing releaseNotes 预览，并输出手动上传指引。.