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/mattrobinsonsre/terrapod/agents-mdgit clone --depth 1 https://github.com/mattrobinsonsre/terrapodWrote 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/mattrobinsonsre/terrapod/agents-md)<a href="https://agentmods.dev/instructions/mattrobinsonsre/terrapod/agents-md"><img src="https://agentmods.dev/badge/instructions/mattrobinsonsre/terrapod/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 | $0.13636 | $0.13636 |
| Opus 5 | $0.06818 | $0.06818 |
| Sonnet 5 | $0.02727 | $0.02727 |
| Haiku 4.5 | $0.01364 | $0.01364 |
Grade A, and why
terrapod 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 yesterday.
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 — 853 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for contributors and AI coding assistants working in the Terrapod
repository. If you are using an AI assistant (Claude Code, Cursor, Copilot,
Aider, etc.), point it at this file — it captures the architecture, the
contracts, the test tiers, and the conventions that keep changes consistent.
For a quick, machine-friendly map of the whole repo — entry points, the
codebase layout, the feature catalogue, and how to enable each feature — see
llms.txt at the repo root.
New here? Start with CONTRIBUTING.md for setup and the
contribution workflow, then come back here for the deeper architecture and
contract rules. Contributions are very welcome — including AI-assisted
("vibe") contributions — as long as they follow the contracts below and
ship with tests.
What Terrapod is
Terrapod is a free, open-source platform replacement for Terraform
Enterprise. It is not a fork of Terraform or OpenTofu — it provides the
collaboration, governance (label-based RBAC and OPA/Rego policy-as-code),
state management, and UI layer that wraps around
terraform or tofu as pluggable execution backends.
Terrapod targets TFE V2 API compatibility for the surface that
terraform, tofu, and tfci consume — service discovery, the
cloud-block run lifecycle, variable + variable-set management, and the module
- provider registry CLI download protocols. That subset is mounted at
/api/v2/and is treated as a stable contract for those clients. Everything else — workspace/role/registry management, agent pools, policy sets (OPA/Rego — the open-source equivalent of TFE's Sentinel), notifications, run tasks, drift detection, the SSE streams, and the runner protocol — is Terrapod-native and lives at/api/terrapod/v1/.
The verified CLI-consumed endpoints are catalogued in
docs/tfe-cli-surface.md. When extending the API:
if a route is on that list it stays at /api/v2/; otherwise it goes under
/api/terrapod/v1/.
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.
- yesterday Changed · +1 lines · +30 tokens per session de514dbaa319
- 5d ago First seen · 852 lines · 13,606 tokens per session scan A 363b29b8a296
terrapod AGENTS.md is an instructions file published in the GitHub repository mattrobinsonsre/terrapod (256 stars, last pushed yesterday), licensed MPL-2.0. It adds 13,636 tokens to every session, about $0.0682 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 2026-08-30.
Other instructions, from other repositories
qovery-skills CLAUDE.md
Claude Code instructions for Qovery/qovery-skills, covering claude.md, layout, core invariants, quick verification commands and every skill.md under 500 lines.
openscreen AGENTS.md
AGENTS.md instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
Claw3D AGENTS.md
Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.
claude-ads CLAUDE.md
Instructions for AgriciDaniel/claude-ads, covering claude ads repository instructions, architecture, development and verification.
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.