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/contextgit 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 | $0.00701 |
| Opus 5 | $0.00000 | $0.00351 |
| Sonnet 5 | $0.00000 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
context 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before executing this command, output:
⚓ shipworthy › command:
/context— analyzing context health and completeness
Run a context health analysis for this project. Invoke the context-manager skill and check these dimensions:
Process
1. Context Infrastructure
Check which standard files exist in .shipworthy/:
| File | Purpose | Status |
|---|---|---|
architecture.md |
Architecture constraints and mandatory rules | exists / missing |
regression-fence.md |
Anti-pattern protection (NEVER/ALWAYS rules) | exists / missing |
config.json |
Project configuration and preset | exists / missing |
INDEX.md |
Memory index (auto-generated) | exists / missing |
learnings/ |
At least one learning file | exists / missing |
sessions/ |
At least one session file | exists / missing |
decisions/ |
Architecture decision records | exists / missing |
plans/ |
Implementation plans | exists / missing |
Also check if CLAUDE.md exists at the project root.
2. Regression Fence Health
- Count rules (H2 headings in
regression-fence.md) - 0 rules = no protection — recommend running
/retroafter next session - 1-15 rules = healthy
- 16-20 rules = near cap, consider pruning stale entries
- Check if any rules reference files/functions that no longer exist in the codebase
3. Session Signals
- Does
.shipworthy/.session-signalsexist? - If yes, count lines — these are unprocessed signals from hooks
- If > 0: recommend running
/retroor starting a new session (auto-retro triggers at session start)
4. Context Completeness
- Estimate total characters loaded at session start (architecture spec + fence + plans + sessions + learnings)
- Show percentage of 8000-char context budget used
- Identify gaps: "You have architecture.md but no regression fence — corrections from past sessions will repeat"
5. Actionable Suggestions
Based on analysis, suggest specific next actions. Examples:
- "12 unprocessed signals — run
/retroto convert them into learnings and fence entries" - "No regression fence yet — it will be auto-created when you run
/retroafter your next work session" - "3 learning files cover overlapping topics —
/retrowill offer to consolidate them" - "Architecture spec missing — start building with
/scaffoldor thearchitecture-awarenessskill" - "CLAUDE.md has no pointer to
.shipworthy/— consider adding:Read .shipworthy/INDEX.md for full project memory"
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 · 77 lines · 0 tokens per session scan A 944c1d71a596
context 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 701 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: Live Truth
Verify live claims with fresh facts, inferences, and unresolved gaps.
VibeGuard: Skill Validate
Gate proposed skills with with/without repair and regression evidence.
VibeGuard: Stats
View hooks trigger statistics - interception/warning/release times and reason analysis.
lrn
Execute the /vibeguard:learn command. $ARGUMENTS.
pf
Execute the /vibeguard:preflight command. $ARGUMENTS.