Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
bmad-code-org avatar

Bmad Os Audit File Refs

  • 1 installs
  • 8 repo stars
  • Updated June 28, 2026
  • bmad-code-org/bmad-utility-skills

bmad-os-audit-file-refs is a skill that audits BMAD workflow and task source files for file-reference convention violations using parallel Haiku subagents.

About

This skill audits BMAD workflow and task source files for file-reference convention violations. A developer runs it to find path references that use relative paths, bare filenames, bare _bmad/ prefixes, or absolute system paths instead of the canonical {project-root}/_bmad/ or {installed_path} forms. It divides the file list into batches of about 20 and spawns parallel Haiku subagents, then reconciles a file count before producing a grouped report.

  • Flags relative, bare-filename, bare _bmad/, and absolute system paths in BMAD source files
  • Spawns parallel Haiku subagents in ~20-file batches
  • Self-check reconciles files-found vs files-checked before reporting

Bmad Os Audit File Refs by the numbers

  • 1 all-time installs (skills.sh)
  • Ranked #1,366 of 1,879 Documentation skills by installs in the Skillselion catalog
  • Data as of Aug 1, 2026 (Skillselion catalog sync)
At a glance

bmad-os-audit-file-refs capabilities & compatibility

Capabilities
file ref audit · convention check · docs audit
Use cases
documentation · refactoring
From the docs

What bmad-os-audit-file-refs says it does

Audit BMAD source files for file-reference convention violations using parallel Haiku subagents.
SKILL.md
Divide the resulting file paths into batches of roughly 20 files each.
SKILL.md
npx skills add https://github.com/bmad-code-org/bmad-utility-skills --skill bmad-os-audit-file-refs

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs1
repo stars8
Last updatedJune 28, 2026
Repositorybmad-code-org/bmad-utility-skills

What it does

Audit BMAD workflow and task source files for file-reference convention violations before shipping a skill or workflow change.

Who is it for?

Maintainers of BMAD-format skill and workflow repos who need to enforce path-reference conventions across many source files.

Skip if: Auditing non-BMAD codebases or general file linting outside the BMAD convention.

When should I use this skill?

A user asks to audit file references for a skill, workflow, or task.

What you get

A grouped report listing each convention-violating file reference by type and location.

By the numbers

  • batches of roughly 20 files each
  • excludes the src/bmm/workflows/4-implementation directory

Files

SKILL.mdMarkdownGitHub ↗

audit-file-refs

Audit new-format BMAD source files for file-reference convention violations using parallel Haiku subagents.

Convention

In new-format BMAD workflow and task files (src/bmm/, src/core/, src/utility/), every file path reference must use one of these valid forms:

  • {project-root}/_bmad/path/to/file.ext — canonical form, always correct
  • {installed_path}/relative/path — valid in new-format step files (always defined by workflow.md before any step is reached)
  • Template/runtime variables: {nextStepFile}, {workflowFile}, {{mustache}}, {output_folder}, {communication_language}, etc. — skip these, they are substituted at runtime

Flag any reference that uses:

  • ./step-NN.md or ../something.md — relative paths
  • step-NN.md — bare filename with no path prefix
  • steps/step-NN.md — bare steps-relative path (missing {project-root}/_bmad/... prefix)
  • ` _bmad/core/tasks/help.md — bare _bmad/ path (missing {project-root}/`)
  • /Users/..., /home/..., C:\... — absolute system paths

References inside fenced code blocks (`` ` ``) are examples — skip them.

Old-format files in src/bmm/workflows/4-implementation/ use {installed_path} by design within the XML calling chain — exclude that directory entirely.

Steps

1. Run this command to get the file list:

   find src/bmm src/core src/utility -type f \( -name "*.md" -o -name "*.yaml" \) | grep -v "4-implementation" | sort

2. Divide the resulting file paths into batches of roughly 20 files each.

3. For each batch, spawn a subagent (subagent_type: "Explore", model: "haiku") with this prompt (fill in the actual file paths):

Read each of these files (use the Read tool on each):
[list the file paths from this batch]

>

For each file, identify every line that contains a file path reference that violates the convention described below. Skip references inside fenced code blocks. Skip template variables (anything containing { that isn't {project-root} or {installed_path}).

>

Valid references: {project-root}/_bmad/..., {installed_path}/..., template variables.
Flag: bare filenames (step-NN.md), ./ or ../ relative paths, bare steps/ paths, bare _bmad/ paths (without {project-root}/), absolute system paths.

>

Return findings as a list:
path/to/file.md:LINE_NUMBER | VIOLATION_TYPE | offending text

>

If a file has no violations, include it as: path/to/file.md | clean

>

End your response with a single line: FILES CHECKED: N where N is the exact number of files you read.

4. Collect all findings from all subagents.

5. Self-check before reporting: Count the total number of files returned by the find command. Sum the FILES CHECKED: N values across all subagent responses. If the totals do not match, identify which files are missing and re-run subagents for those files before proceeding. Do not produce the final report until all files are accounted for.

6. Output a final report:

  • Group findings by violation type
  • List each finding as file:line — offending text
  • Show total count of violations and number of affected files
  • If nothing found, say "All files conform to the convention."

Related skills

Documentationdocsintegrations

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.