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 agentmods add commands/vimalk0703/shipworthy/validategit clone --depth 1 https://github.com/Vimalk0703/shipworthyWhat 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 | $0.00000 | $0.00401 |
| Opus 5 | $0.00000 | $0.00200 |
| Sonnet 5 | $0.00000 | $0.00080 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
validate 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 2d 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.
What it actually says
Before executing this command, output:
⚓ shipworthy › command:
/validate— running pre-push validation suite
/validate — Pre-Push Validation Gate
Run the comprehensive Shipworthy validation suite before pushing changes.
What This Does
Dispatches the pre-push-validator agent to run all validation checks against the current state of the repository. This catches issues before they reach CI.
Steps
- Run
bash tests/validate-all.shto execute the full validation suite - Report results grouped by category:
- Hook tests — session-start, pre-tool-use, post-tool-use (37 tests)
- Skill frontmatter — name, description, invoke_when fields on all skills
- CSO compliance — invoke_when starts with "Use when...", length limits, name/directory match
- Skill routing — all skills reachable from the master routing table
- Cross-references — all shipworthy:skill-name references resolve to real skills
- Skill quality — no duplicates, minimum content, anti-patterns sections, markdown structure
- Repo structure — required files, directories, agents, templates, commands, secrets scan
- If any check fails, list the specific failures and suggest fixes
- If all checks pass, confirm it is safe to push
When to Run
- Before every
git push - After adding or modifying skills
- After changing hooks
- Before creating a PR
- When the user runs
/validate
Output Format
Report results as a clear summary table:
| Check | Status | Details |
|---|---|---|
| Hook tests | PASS/FAIL | 37/37 passed |
| Skill frontmatter | PASS/FAIL | 55/55 valid |
| CSO compliance | PASS/FAIL | All "Use when..." |
| ... | ... | ... |
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.
- 2d ago First seen · 46 lines · 0 tokens per session scan A 66756f0fd103
validate is a command published in the GitHub repository Vimalk0703/shipworthy (7 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 401 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 2026-08-31.
Other commands, from other repositories
VibeGuard: Learn
Dual-mode learning: (A) Extract guard rules from errors (B) Extract reusable skills from discoveries. Automatic mode routing.
VibeGuard: Skill Validate
Gate proposed skills with with/without repair and regression evidence.
VibeGuard: Live Truth
Verify live claims with fresh facts, inferences, and unresolved gaps.
VibeGuard: Stats
View hooks trigger statistics - interception/warning/release times and reason analysis.
pf
Execute the /vibeguard:preflight command. $ARGUMENTS.
lrn
Execute the /vibeguard:learn command. $ARGUMENTS.