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 instructions/adhocteam/cloud-gov-instructions/agents-mdgit clone --depth 1 https://github.com/adhocteam/cloud-gov-instructionsWrote 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/instructions/adhocteam/cloud-gov-instructions/agents-md)<a href="https://agentmods.dev/instructions/adhocteam/cloud-gov-instructions/agents-md"><img src="https://agentmods.dev/badge/instructions/adhocteam/cloud-gov-instructions/agents-md.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 | $0.00844 | $0.00844 |
| Opus 5 | $0.00422 | $0.00422 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
cloud-gov-instructions AGENTS.md 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 4d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Autonomy tiers
Default to the lowest tier that accomplishes the task. Never skip tiers.
| Tier | Mode | What the agent does |
|---|---|---|
| 0: OBSERVE | Read-only | Run read-only CF commands, analyze logs, review configurations |
| 1: RECOMMEND | Suggest only | Analyze and suggest changes without modifying anything |
| 2: DRAFT | Edit files | Create or modify local files (manifests, CI workflows, code) |
| 3: DEPLOY (non-prod) | Execute in dev/staging | Run modifying CF commands in non-production spaces after confirmation |
| 4: DEPLOY (prod, gated) | Execute in production | Requires explicit confirmation and impact statement before any modifying command |
CF command safety
Always ask for explicit user confirmation before running any CF CLI command that modifies or destroys resources.
If the space name contains prod, production, or prd, state the org, space, app name, and impact before proceeding.
Commands that always require confirmation
| Command | Risk | Impact |
|---|---|---|
cf delete |
HIGH | Permanently deletes an application |
cf delete-service |
HIGH | Permanently deletes a service and its data |
cf unbind-service |
MEDIUM | Disconnects app from service, may cause errors |
cf delete-service-key |
MEDIUM | Revokes external access credentials |
cf stop |
MEDIUM | Stops application, causes downtime |
cf delete-route |
MEDIUM | Removes route, breaks external access |
cf unmap-route |
MEDIUM | Removes route mapping from app |
cf push |
MEDIUM | Deploys code, may introduce bugs |
cf restage |
MEDIUM | Rebuilds app, causes brief downtime |
cf restart |
LOW | Restarts app, causes brief downtime |
cf scale |
LOW | Changes resources, may affect availability |
cf set-env |
LOW | Changes configuration, requires restart |
cf update-service |
LOW | Modifies service configuration |
Commands safe to run without confirmation
cf apps, cf app, cf services, cf service, cf logs --recent, cf env, cf routes, cf marketplace, cf target, cf buildpacks
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.
- 4d ago First seen · 76 lines · 844 tokens per session scan A 1161d303c2ba
cloud-gov-instructions AGENTS.md is an instructions file published in the GitHub repository adhocteam/cloud-gov-instructions (10 stars, last pushed 5mo ago), licensed MIT. It adds 844 tokens to every session, about $0.0042 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 instructions, from other repositories
azure-search-openai-demo bicep.instructions.md
Infrastructure as Code with Bicep.
optio CLAUDE.md
Instructions for jonwiggins/optio, covering claude.md, what is optio?, architecture, pod-per-repo with worktrees and worktree lifecycle.
obsidian-copilot CLAUDE.md
Claude Code instructions for logancyang/obsidian-copilot, a project described as: THE Copilot in Obsidian.
apex-accelerator iac-terraform-best-practices.instructions.md
Terraform-specific IaC best practices for Azure templates. AVM-first, CAF naming, security baseline, provider pins.
apex-accelerator iac-bicep-best-practices.instructions.md
Bicep-specific IaC best practices for Azure templates. Security baseline, naming, AVM mandate, anti-patterns.
apex-accelerator governance-discovery.instructions.md
MANDATORY Azure Policy discovery requirements for governance constraints.