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 skills add cobusgreyling/grok-build-showcase --skill project-auditorgit clone --depth 1 https://github.com/cobusgreyling/grok-build-showcaseWrote 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/skills/cobusgreyling/grok-build-showcase/project-auditor)<a href="https://agentmods.dev/skills/cobusgreyling/grok-build-showcase/project-auditor"><img src="https://agentmods.dev/badge/skills/cobusgreyling/grok-build-showcase/project-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cobusgreyling/grok-build-showcase/project-auditor"><img src="https://agentmods.dev/badge/skills/cobusgreyling/grok-build-showcase/project-auditor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00101 | $0.01198 |
| Opus 5 | $0.00051 | $0.00599 |
| Sonnet 5 | $0.00020 | $0.00240 |
| Haiku 4.5 | $0.00010 | $0.00120 |
Grade A, and why
project-auditor 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 10d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Auditor Skill
You are an expert at evaluating how well a codebase is set up for productive use with Grok Build (and similar agentic coding tools).
Goals
- Give an accurate 0-100 "Grok Readiness Score".
- Identify concrete strengths and gaps.
- Provide prioritized, actionable recommendations.
- Support both human-readable and machine-readable output.
Steps
-
Understand the target
- Accept a directory path (default to current working directory or
.). - Confirm the path exists using list_dir or run_terminal_command (
lsortest -d).
- Accept a directory path (default to current working directory or
-
Load ignore rules
- Read
.grokignore(if present) and.gitignore(if present) from the target root. - Build an effective ignore matcher (respect both; .grokignore takes precedence for agent reads).
- Never read files that would be ignored (node_modules, dist, .grok/sessions, large binaries, logs, etc.).
- Read
-
Scan for Grok Build signals (use list_dir + read_file + grep selectively)
- Look for project rule files in this priority:
AGENTS.md,Agents.md,AGENT.md,CLAUDE.mdetc. (see official project-rules docs). - Count and inspect files under
.grok/skills/*/SKILL.md. - For each skill: read the frontmatter, verify
name+descriptionexist and description is specific. - Detect test frameworks:
package.json→ look forvitest,jest,mocha,ava,tap,scripts.testpyproject.toml/pytest.ini/setup.cfgfor pytestgo.mod+_test.gofiles, etc.
- Detect CI:
.github/workflows/(any*.ymlor*.yaml).gitlab-ci.yml,Jenkinsfile,circle.yml,buildkite.yml, etc.
- Git hygiene:
- Is it a git repo? (
git rev-parse --is-inside-work-tree) - Recent commits, clean/dirty status, branch name.
- Is it a git repo? (
- Other positive signals: README with "Grok", "agent", or "Plan Mode" mentions; CONTRIBUTING.md; .grok/ other dirs (hooks, agents).
- Look for project rule files in this priority:
-
Score the project (0-100) Base scoring on these weighted signals (adjust reasonably for project type):
- AGENTS.md (or equivalent) present and substantial (≥800 chars, has multiple clear sections): +25
- At least 2-3 well-formed skills in
.grok/skills/: +20 - Real test setup with passing tests or clear test command: +20
- CI configuration present: +10
- Good ignore hygiene (.grokignore present or comprehensive .gitignore): +8
- Recent, clean git history + sensible branch discipline: +7
- Bonus for explicit verification language ("run tests before commit", "use check skill", Plan Mode guidance): +5-10
- Penalties for anti-patterns (huge unignored node_modules in scans, no tests, AGENTS.md is just a one-liner, etc.)
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.
- 10d ago First seen · 86 lines · 101 tokens per session scan A 548df9e0c18a
project-auditor is a skill published in the GitHub repository cobusgreyling/grok-build-showcase (2 stars, last pushed 3mo ago), licensed MIT. It adds 101 tokens to every session and 1,198 once invoked, about $0.0005 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 skills, from other repositories
housekeeping
A periodic maintenance pass: backlog hygiene, docs/changelog currency, release check, worktree/branch prune, dependency triage, CI/test green, drift audits.
ci-flaky-patrol
Classify a bounded batch of stale PR CI failures and choose the safest response.
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
atmos-modernization
Atmos Modernization: migrate deprecated or legacy Atmos patterns to current names, Native CI, Atmos Pro drift detection, dependencies.components, nametemplate, and declared secrets.
issue-creator
A guide for turning unclear user feedback from text, chat excerpts, or screenshots into a focused GitHub issue, a tracked software-work item. It preserves the original request and separates evidence from information that is still unknown.
status
Surfaces the current state of work in gflow-cli. Three variants at different levels of detail: full state (status), next task only (next), active plan identity (active). All variants run scripts/dev/activeplan.py and filter its output to the requested detail level.