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 jubscodes/get-shit-pretty --skill gsp-doctorgit clone --depth 1 https://github.com/jubscodes/get-shit-prettyWrote 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/jubscodes/get-shit-pretty/gsp-doctor)<a href="https://agentmods.dev/skills/jubscodes/get-shit-pretty/gsp-doctor"><img src="https://agentmods.dev/badge/skills/jubscodes/get-shit-pretty/gsp-doctor/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/jubscodes/get-shit-pretty/gsp-doctor"><img src="https://agentmods.dev/badge/skills/jubscodes/get-shit-pretty/gsp-doctor.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 | $0.00000 | $0.01284 |
| Opus 5.5 | $0.00000 | $0.00514 |
| Sonnet 5.5 | $0.00000 | $0.00257 |
| Haiku 4.5 | $0.00000 | $0.00128 |
Grade A, and why
gsp-doctor 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 2mo 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checks: structure, phase ordering, stale outputs, config drift, missing chunks, broken references, review status, brand drift, upgrade detection
Check for .design/ in the current directory.
If not found:
🩺 GSP Doctor — No project found
No .design/ directory detected. Run /gsp-start to start.
Stop here.
Step 1: Detect structure type
New dual-diamond structure: .design/branding/ or .design/projects/ exists
Legacy flat structure: .design/config.json exists at root (not inside branding/ or projects/)
Empty: .design/ exists but has neither
For legacy: run legacy checks (same as v0.3.0 doctor). For new: run multi-instance checks below.
Step 2: Scan all instances
Brands: List all directories in .design/branding/ that have a config.json with project_type: "brand"
Projects: List all directories in .design/projects/ that have a config.json with project_type: "design"
For each instance, read:
config.json— configurationSTATE.md— phase progressBRIEF.md— briefbrand.ref— brand reference (projects only)
Step 3: Run checks per instance
Load ${CLAUDE_SKILL_DIR}/checks.md — the full check catalog with pass/warn/fail criteria. Read it once at this step; do not load it before Step 2 because the applicable check sets depend on what was scanned.
Run only the sets applicable to the detected state:
| Detected | Run |
|---|---|
| Each brand instance | B1, B2, B3, B4 |
| Each project instance | P1–P10 |
| Always (installation) | I1, I2, I3, I4, I5 |
Project has implementation_target: shadcn and .design/system/STACK.md exists |
S1–S5 |
| Multiple projects reference the same brand | X1 |
For each check, record the verdict (PASS/WARN/FAIL/INFO) plus a short instance-tagged message for issues.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 150 lines · 0 tokens per session scan A 65c5f22089f0
gsp-doctor is a skill published in the GitHub repository jubscodes/get-shit-pretty (55 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,284 tokens. 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.
gsp-doctor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gsp-doctorjubscodes/get-shit-pretty | Skill | 55 | 5mo ago | MIT | A | 0 | Claude Code |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 61 | Claude Code |
| mcplsbug-ops/mcpls | Skill | 81 | 3d ago | Apache-2.0 | A | 89 | Claude Code, Codex |
| patch-editwolfenazz/YzPzCode | Skill | 20 | 2d ago | Apache-2.0 | A | 30 | Claude Code, Codex |
| od-code-migrationwolfenazz/YzPzCode | Skill | 20 | 2d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| module-federationsoulcodex/agentic | Skill | 10 | 8d ago | MIT | A | 51 | Claude Code, Codex |
| static-code-analysissoulcodex/agentic | Skill | 10 | 8d ago | MIT | A | 65 | Claude Code, Codex |