Tirith Standards

What it does

When your agent uses it

• Asked to add guardrails to a repository that has no policies yet
• Enforce a tagging
• Naming standard
• Codify a team convention

Example prompts

• “/tirith-standards”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Inventory the repository. List every distinct resource "TYPE" "NAME" across .tf and
2. 2Extract the conventions already there. Read the existing code before proposing rules. What
3. 3Propose before writing. Give the user a table: standard, the resource types it would cover,
4. 4Write one file per standard, under .tirith/policies/, named for the rule
5. 5Prove each one. For every policy, produce a plan document that violates it and confirm
6. 6Report what you could not express. Name the standard, name what Tirith would need, and stop.

What it can do on your machine

Read from SKILL.md and the folder at commit 4a3411e. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • terraform

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • stackguardian.github.io

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tirith Standards loads about 2k tokens when it runs. Until then it costs about 125 tokens; SKILL.md has 1,039 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~125

When it runs · the whole SKILL.md, loaded when a task matches

~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from StackGuardian/tirith at commit 4a3411e, republished under its Apache-2.0 licence (© StackGuardian). 1,039 words, ~1,989 tokens.

name

tirith-standards

description

Generate a Tirith policy set for an existing Terraform or OpenTofu repository, covering organization standards such as required tags, naming conventions, allowed regions, permitted resource types, sizes and encryption defaults. Use when asked to add guardrails to a repository that has no policies yet, to enforce a tagging or naming standard, to codify a team convention, or to produce a starting policy set from existing IaC. Requires the tirith-policies skill for the vocabulary.

severity > error_tolerance  ->  the check FAILS
otherwise                   ->  the check is SKIPPED

{
  "evaluators": [
    {"id": "not_applicable",
     "provider_args": {"operation_type": "count", "terraform_resource_type": "aws_s3_bucket"},
     "condition": {"type": "Equals", "value": 0}},
    {"id": "the_rule", "provider_args": {"...": "..."},
     "condition": {"type": "RegexMatch", "value": "...", "error_tolerance": 1}}
  ],
  "eval_expression": "not_applicable || the_rule"
}

© StackGuardian, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files in .claude/skills/tirith-standards of StackGuardian/tirith.

• SKILL.md
• examples/org-standards/README.md
• examples/org-standards/naming.json
• examples/org-standards/no-bucket.json
• examples/org-standards/should-fail.json
• examples/org-standards/should-pass.json
• reference/standards.md

Open the folder on GitHubat commit 4a3411e