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.
git clone --depth 1 https://github.com/dmytri/shipshapeWrote 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/commands/dmytri/shipshape/status)<a href="https://agentmods.dev/commands/dmytri/shipshape/status"><img src="https://agentmods.dev/badge/commands/dmytri/shipshape/status/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/commands/dmytri/shipshape/status"><img src="https://agentmods.dev/badge/commands/dmytri/shipshape/status.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 | $0.00013 | $0.00316 |
| Opus 5.5 | $0.00005 | $0.00126 |
| Sonnet 5.5 | $0.00003 | $0.00063 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
status 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 1mo 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
Shipshape status
This command mechanizes the derived-state rule from the Shipshape skills: harbour and deck state are derived from durable signals, never stored. Doctrine lives in the skills; this command adds none.
Derive current deck state from repository signals and report it. Run read-only checks. Change nothing.
- Tree: run
git status --shortand, when an upstream exists,git rev-list --count @{upstream}..HEAD. Report working tree cleanliness and commits ahead of upstream. - Rigging: report whether
RIGGING.mdexists at the project root and whether the required values are present:languageunder Stack,implementationandspecsunder Directories,focusedunder Commands, andperturbunder Perturbation. - Harbour signals: count
@captainand@shipwrighttags in the specs directory. - Perturbations: count
PERTURBATIONstatements in the implementation directory. - Watchbill: report whether
watchbill.jsonexists and matches the fixed watchbill shape the shipshape skill defines. - Report the signals as a short table. Close with the suggested entry:
RIGGING.mdabsent routes to/shipwrightfor fitting out, per theshipshapeskill's Entry; a dirty tree needs Boatswain, per the Captain skill; otherwise Captain.
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.
- 1mo ago First seen · 18 lines · 13 tokens per session scan A fea14e0d1d24
status is a command published in the GitHub repository dmytri/shipshape (7 stars, last pushed 2mo ago), licensed 0BSD. It adds 13 tokens to every session and 316 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
ng-deficiency
Portable command prompt generated from skills/tracking-deficiencies/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
backlog
PitWay: Capture out-of-scope work discovered mid-task, without expanding current scope.
feature-track-init
Initialize Feature Track in this repository.
work
Work unit management: list, continue, checkpoint, switch.
skraft-refine
Review one GitHub issue and post its refinement proposal as a comment — Definition of Ready, Fibonacci size, proposed story, domain examples, acceptance criteria, defects of the current criteria. Runs with your own model and credentials.
opsx-review-set
Set OpenAI-compatible artifact review provider, model, effort, budget, or blocking for a session stage.