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 runwhen-contrib/runwhen-platform-mcp --skill discover-secretsgit clone --depth 1 https://github.com/runwhen-contrib/runwhen-platform-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/runwhen-contrib/runwhen-platform-mcp/discover-secrets)<a href="https://agentmods.dev/skills/runwhen-contrib/runwhen-platform-mcp/discover-secrets"><img src="https://agentmods.dev/badge/skills/runwhen-contrib/runwhen-platform-mcp/discover-secrets.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00082 | $0.01370 |
| Opus 5 | $0.00041 | $0.00685 |
| Sonnet 5 | $0.00016 | $0.00274 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
discover-secrets 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 6d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discover Secrets
Find and configure the right secrets for an SLX script by searching available workspace secrets and inferring from platform tags and existing SLX configurations.
How secrets work in RunWhen
Most secrets are not stored in RunWhen — they are configured locally on runner locations (private runners). The workspace secret list (get_workspace_secrets) returns key names that map to secrets already provisioned on the runner's filesystem or environment.
When a script runs, mapped secrets are injected as file paths in environment variables:
# In your script
token_path = os.environ.get("USER_TOKEN") # This is a FILE PATH, not the value
with open(token_path) as f:
token = f.read().strip()
The read_secret helper pattern handles both file-based (runner) and direct-value (local testing) cases:
def read_secret(env_var):
val = os.environ.get(env_var, "")
if val and os.path.isfile(val):
with open(val) as f:
return f.read().strip()
return val.strip()
Discovery workflow
Step 1: List available secrets
get_workspace_secrets(workspace_name="my-workspace")
This returns vault key names when the workspace secrets API lists them. When the
vault list is empty, the response includes secrets_from_slxs: env-var →
workspaceKey patterns copied from committed SLX runbooks (e.g.
k8s:file@secret/kubeconfig:kubeconfig).
Use secret_vars_for_author_run (full workspaceKey values) for
run_script, run_script_and_wait, and commit_slx — not bare vault names
like "kubeconfig": "kubeconfig" unless that value is already a workspaceKey.
The MCP server auto-expands short keys when it can infer them from SLXs.
Step 2: Infer from platform and context
Secret names often follow naming conventions tied to the platform or environment:
| Platform / Use Case | Likely secret names | Notes |
|---|---|---|
| Kubernetes | kubeconfig |
Almost always present; the standard name |
| RunWhen PAPI (beta) | BETA-USER_TOKEN, beta_tok1 |
JWT tokens for beta environment |
| RunWhen PAPI (prod) | USER_TOKEN, PROD-USER_TOKEN |
JWT tokens for production |
| GitHub | *-REPO-TOKEN, RUNWHEN-REPO-TOKEN |
PATs for repo access |
| Slack | slack |
Webhook URLs or bot tokens |
| GCP | *-sa, ops-suite-sa, gcp-* |
Service account JSON keys |
| Azure | *-clientId, *-clientSecret, *-tenantId, *-subscriptionId |
Azure SP credentials (often as a set of 4) |
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.
- 6d ago First seen · 138 lines · 82 tokens per session scan A 90220db9f2d8
discover-secrets is a skill published in the GitHub repository runwhen-contrib/runwhen-platform-mcp (1 stars, last pushed 23d ago), licensed Apache-2.0. It adds 82 tokens to every session and 1,370 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 2026-08-31.
Other skills, from other repositories
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
n8n-self-hosting
Deploy a production self-hosted n8n end-to-end to a fresh Linux VM over SSH, using Docker Compose behind a Caddy reverse proxy with automatic HTTPS. Use whenever the user wants to self-host, install, set up, provision, or deploy n8n on their own server/VPS/box (Hetzner, DigitalOcean, AWS EC2, bare metal, etc.) — in…
cloud-run
Manage Cloud Run services and jobs.
modal
Use when the user needs to run isolated code remotely — a disposable container, optional GPU access (T4 → H100), or a safer place for untrusted / heavy code. Prefer local execution for normal repo work; use Modal sandboxes for isolation, hardware access, or one-shot heavy compute.
cluster-events
Analyze cluster-wide Kubernetes events to identify issues and patterns. Aggregates Warning events, detects high-frequency patterns, and correlates related events.
k8s-pod-rightsizer
Analyze Kubernetes workload metrics and produce policy-constrained CPU/memory rightsizing recommendations with optional patch generation and rollback-safe apply.