runwhen-task-contract

A set of rules for writing scripts that RunWhen can execute as tasks or service-level indicators. A service-level indicator is a numeric measure of how well a service is operating.

In plain words
What is it for?
Use it while writing or checking Python and Bash tasks, reporting issues and severity, returning indicator scores, handling injected secrets, and assigning required access and data tags.
Why use it?
It prevents scripts from being rejected or producing unusable results because they do not follow RunWhen's required input, output, and secret-handling format.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/runwhen-contrib/runwhen-platform-mcp/runwhen-task-contract
Clone the repo
git clone --depth 1 https://github.com/runwhen-contrib/runwhen-platform-mcp
Per session 283 This file is loaded in full into every session.
When invoked 283 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00283 $0.00283
Opus 5 $0.00142 $0.00142
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00028 $0.00028

Measured 2d ago against content hash fa1eb05783e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runwhen-task-contract 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.

rules/runwhen-task-contract.mdc · 17 lines

What it actually says

runwhen-task-contract:

  • Before writing any RunWhen task or script, call get_workspace_context to load the project's RUNWHEN.md rules.
  • Python tasks must define a top-level main() that returns List[Dict] with keys: issue title, issue description, issue severity (1-4), issue next steps.
  • Python SLIs must define main() returning a float between 0 and 1.
  • Bash tasks must define main() and write issue JSON to file descriptor 3 (>&3).
  • Bash SLIs must define main() and write a float to file descriptor 3.
  • Never call main() directly or use if __name__ == "__main__" — the runner invokes it.
  • Secret vars are injected as env vars pointing to file paths (e.g. kubeconfig is a path, set KUBECONFIG=$kubeconfig).
  • Use validate_script before run_script to catch contract violations early.
  • When committing with commit_slx, always set the access tag (read-write or read-only) and data tag (logs-bulk, config, or logs-stacktrace).
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. 2d ago First seen · 17 lines · 283 tokens per session scan A fa1eb05783e0

Subscribe to this mod's changes

runwhen-task-contract is a cursor rule published in the GitHub repository runwhen-contrib/runwhen-platform-mcp (1 stars, last pushed 18d ago), licensed Apache-2.0. It adds 283 tokens to every session, about $0.0014 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.