Align

What it does

When your agent uses it

• You want to check health of the codebase
• Verify convention compliance
• Get a scored report
• Find violations

Example prompts

• “check conventions”
• “alignment scan”
• “codebase health”
• “/align”

Workflow steps

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

1. 1Parse scope from $ARGUMENTS (default: full scan)
2. 2Dispatch the convention-eval agent with the scope
3. 3Display the report to the user

What it can do on your machine

Read from SKILL.md and the folder at commit 57e8af8. 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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).

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

• Network

  No URLs in SKILL.md.

  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

Align loads about 754 tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 217 words of instructions outside code blocks.

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

~114

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

~754

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 ambient-code/platform at commit 57e8af8, republished under its MIT licence (© ambient-code). 217 words, ~754 tokens.

name

align

description

Run a convention alignment check across the codebase to measure adherence to documented standards. Use when you want to check health of the codebase, verify convention compliance, get a scored report, find violations, check alignment before a release, or run periodic quality scans. Triggers on: "check conventions", "alignment scan", "codebase health", "are we following our standards", "convention violations", "quality check", "how aligned are we".

/align                # Full codebase scan
/align backend        # Backend checks only
/align frontend       # Frontend checks only
/align operator       # Operator checks only
/align runner         # Runner checks only
/align security       # Security checks only

$ARGUMENTS

Agent({
  description: "Convention alignment check",
  prompt: "You are the convention-eval agent. Read your definition at .claude/agents/convention-eval.md, then run a ${scope} convention alignment check. Scope: ${scope} (one of: full, backend, frontend, operator, runner, security). Load all context files listed in your definition, run the checks, and report findings in the standard output format with scores."
})

© ambient-code, MIT. 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 1 other file in skills/align of ambient-code/platform.

• SKILL.md
• evals/evals.json

Open the folder on GitHubat commit 57e8af8