Borrowing it
Nothing to install: this file belongs to ruah-dev/ruah-orch. 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/ruah-dev/ruah-orch/main/.claude/skills/pre-start-context/SKILL.mdgit clone --depth 1 https://github.com/ruah-dev/ruah-orchWrote 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/ruah-dev/ruah-orch/pre-start-context)<a href="https://agentmods.dev/skills/ruah-dev/ruah-orch/pre-start-context"><img src="https://agentmods.dev/badge/skills/ruah-dev/ruah-orch/pre-start-context.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 | $0.00040 | $0.03669 |
| Opus 5 | $0.00020 | $0.01835 |
| Sonnet 5 | $0.00008 | $0.00734 |
| Haiku 4.5 | $0.00004 | $0.00367 |
Grade C, and why
pre-start-context scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `rm -rf` on paths above the project root, `/`, `~`, `$HOME` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Network:** Only access resources explicitly required by the task (package registries, CI APIs, documented endpoints). NEVER pipe remote content to a shell (`curl|bash`, `wget|sh`). How it starts
The opening of the file, as written. The whole thing — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pre-start-context
Run this before starting any task. It discovers the project, loads cross-session knowledge, and applies your governance rules — all from the filesystem, nothing hardcoded.
Chain: pre-start → task → /post-start-validation. Do not skip post-start.
0. Execution Policy
Read .claude/governance.md for project-specific rules. If it exists, its policies override defaults below.
Sandbox Boundaries
All tools and subagents MUST operate within these limits:
- Filesystem: Write/delete ONLY within this repository (
git rev-parse --show-toplevel). Read access is broader for discovery, but mutations stay in-repo. - Network: Only access resources explicitly required by the task (package registries, CI APIs, documented endpoints). NEVER pipe remote content to a shell (
curl|bash,wget|sh). - System: NEVER modify system files, global packages, PATH, system services, or environment outside this process.
- Destructive commands — NEVER run:
rm -rfon paths above the project root,/,~,$HOMEdd,mkfs,fdisk,parted(raw disk operations)shutdown,reboot,halt,init 0/6DROP TABLE/DATABASE/SCHEMAwithout explicit user confirmationdocker system prune -a,kubectl delete namespacegit push --forceto main/masterchmod -R 777or recursive permission changes outside repo
- Subagents: Spawned agents inherit these boundaries. Agent definitions should include
## Boundariesreferencing these rules. Subagents MUST NOT escalate their own permissions.
The
sandbox-guard.shhook enforces these rules at the system level. Even if instructions are misread, destructive commands are hard-blocked.
Default AUTO-EXECUTE (unless governance overrides):
- Reading files, build, compile, test, lint, format, git operations, package management, environment checks
- Any command operating on files within this repository
Default ASK FIRST:
- Destructive infrastructure (rm containers, drop databases, delete volumes)
- Production deployments
- Secrets/credentials modification
- System-level changes outside this repository
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 · 492 lines · 40 tokens per session scan C 852d0801d75d
pre-start-context is a skill published in the GitHub repository ruah-dev/ruah-orch (11 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 3,669 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…