ClawRouter is a local service that chooses among language models for each request and handles payment for their use. Autonomous agents use it to access multiple LLM providers through one routing and billing system.
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 BlockRunAI/ClawRouter --skill releasegit clone --depth 1 https://github.com/BlockRunAI/ClawRouterWrote 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/blockrunai/clawrouter/release)<a href="https://agentmods.dev/skills/blockrunai/clawrouter/release"><img src="https://agentmods.dev/badge/skills/blockrunai/clawrouter/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.
<a href="https://agentmods.dev/skills/blockrunai/clawrouter/release"><img src="https://agentmods.dev/badge/skills/blockrunai/clawrouter/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.01367 |
| Opus 5.5 | $0.00018 | $0.00547 |
| Sonnet 5.5 | $0.00009 | $0.00273 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
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 1mo 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawRouter Release Checklist
This skill is mandatory for every release. Execute every step in order. Do not skip.
Step 1: Confirm the New Version
Read the current version:
cat package.json | grep '"version"'
Ask: "What version are we releasing?" Confirm it follows semver and is higher than current.
Step 2: Update package.json Version
Edit package.json — bump "version" to the new version.
Step 3: Write CHANGELOG Entry
Open CHANGELOG.md. Add a new section at the top (after the header) in this format:
## v{VERSION} — {DATE}
- **Feature/Fix name** — description
- **Feature/Fix name** — description
Rules:
- Date format:
Mar 8, 2026 - One bullet per logical change
- Every bullet must be present — no "see git log"
- Include all changes since the previous release
Step 4: Confirm No Manual Server Sync Required
No file edit needed here. Earlier releases (pre-v0.12.x) required manually
updating a CURRENT_CLAWROUTER_VERSION constant in blockrun's
src/app/api/v1/chat/completions/route.ts. That constant has been replaced:
the server now fetch-es https://registry.npmjs.org/@blockrun/clawrouter/latest
at process startup and uses the returned version to drive the
update_available hint embedded in 429 responses to outdated clients.
// blockrun/src/app/api/v1/chat/completions/route.ts
let latestClawRouterVersion: string | null = process.env.CLAWROUTER_CURRENT_VERSION || null;
fetch("https://registry.npmjs.org/@blockrun/clawrouter/latest", {
signal: AbortSignal.timeout(5000),
})
.then((r) => r.json())
.then((data) => {
if (data.version) latestClawRouterVersion = data.version;
})
.catch(() => {
/* keep env var fallback */
});
Implications:
- The
npm publishin Step 11 IS the entire "sync blockrun" action. After that step lands, the next blockrun server restart will fetch and surface the new version. No manual constant edit. No separate PR in the blockrun repo. CLAWROUTER_CURRENT_VERSIONenv var is the cold-start fallback (used only when the registry fetch fails). It exists for resilience, not as the primary mechanism — don't touch it on every release.- Verification of the user-facing update nudge happens in Step 12 via
npm view @blockrun/clawrouter version(the same registry endpoint blockrun's server hits).
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.
- 1mo ago First seen · 211 lines · 44 tokens per session scan A 072804f07d2a
release is a skill published in the GitHub repository BlockRunAI/ClawRouter (6,627 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,367 once invoked, about $0.0002 per session on Opus 5.5. 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
release
Release a new version of the DevoxxGenie IntelliJ plugin — prompt for the target version, bump it in the build files, write a curated CHANGELOG.md entry and plugin.xml change-notes from the git/PR history since the last tag, build to verify, then commit, tag, and publish a matching GitHub release. Use this whenever…
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.
argocd-expert
Expert-level ArgoCD GitOps deployment, application management, sync strategies, and production operations. Use when the user mentions GitOps, Kubernetes, continuous deployment, declarative, or automation, or when the task involves ArgoCD Architecture, Application CRD, AppProject, or ApplicationSet.
git-expert
Expert-level Git version control with advanced workflows, branching strategies, and best practices for team collaboration. Use when the user mentions version control, collaboration, or workflow, or when the task involves Essential Git Commands, Advanced Git Techniques, Branching Strategies, or Conflict Resolution.
version-bump
Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging, GitHub releases, and changelog generation. Ends with the agent running npm publish itself using the maintainer's npm…
update-v8-version
Update Codex's pinned v8 / rustyv8 versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update rustyv8 artifacts, prepare or validate a V8 release candidate, check v8-canary, or diagnose why a V8 version update no longer builds.