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/aadivar/shiplog/featuregit clone --depth 1 https://github.com/aadivar/shiplogWrote 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/aadivar/shiplog/feature)<a href="https://agentmods.dev/commands/aadivar/shiplog/feature"><img src="https://agentmods.dev/badge/commands/aadivar/shiplog/feature.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00479 |
| Opus 5 | $0.00000 | $0.00239 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
feature 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 4d 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
/shiplog feature
Create a new feature file and add it to the PRD.
Trigger
User runs /shiplog feature "<name>" or /shiplog feature
Behavior
Step 1: Validate setup
Check that .shiplog/config.json exists and docs/PRD.md exists. If not:
"Shiplog is not initialized. Run
/shiplog initfirst."
Step 2: Get feature name
- If the user provided a name as an argument (e.g.,
/shiplog feature "user auth"), use that - If no name was provided, ask: "What's the feature name?"
Step 3: Assign feature ID
Read docs/PRD.md and find the highest existing feature ID (e.g., F003).
Assign the next sequential ID (e.g., F004).
Step 4: Get current sprint
Read docs/PROGRESS.md to determine the current sprint number.
Step 5: Create feature file
Read the template from templates/feature.md.hbs and create the feature file:
- Path:
docs/features/{featureId}-{kebab-case-name}.md - Replace template variables:
{{featureId}}— e.g., F004{{featureName}}— The feature name provided by user{{sprint}}— Current sprint number{{date}}— Today's date (YYYY-MM-DD)
Step 6: Add to PRD
Append a new row to the feature table in docs/PRD.md:
| {ID} | {name} | not-started | {sprint} | |
Step 7: Confirm
Created feature {ID} — {name}
File: docs/features/{ID}-{kebab-name}.md
Sprint: {N}
Status: not-started
Edit the feature file to add description and acceptance criteria.
Rules
- Feature IDs are always sequential (F001, F002, F003...)
- Feature file names use kebab-case (F004-user-authentication.md)
- Never overwrite an existing feature file
- If a feature with the same name already exists, warn the user
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.
- 4d ago First seen · 55 lines · 0 tokens per session scan A 9135674c329d
feature is a command published in the GitHub repository aadivar/shiplog (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 479 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
sm-sail
Command "sm-sail" from ScienceIsNeato/slop-mop, covering /sm-sail — drive a pr to green, autonomously, the loop, when sail parks on review threads, when to stop before "pr ready" — only two reasons and expect convergence, not one pass.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
sm-buff
You usually don't run buff directly — run sm sail. sm sail drives the whole PR to green and calls buff watch / triage for you, stopping only when it needs you to act (see /sm-sail). Reach for sm buff here only for surgical work: inspecting a specific failure, or resolving a single review thread when sail has parked on…
sm-wake-angry-drunk-captain
The last-resort verb. Use it ONLY when the loop is genuinely exhausted: barnacles filed, gates green or truly unfixable, and the single remaining move is a human judgment call no sm verb can make for you.
sm-barnacle
Use when sm itself gives invalid guidance, blocks valid work, produces confusing output, or breaks install/upgrade/refit flow. Do not use this for real target-repo failures; fix those through the normal rail.
sm-init
Run when you find a repo with sm installed but no .sbconfig.json — or after upgrading slopmop to pick up new gates.