terse-sharp: Command for Claude Code

.claude/commands/ship-improvements.md

ship-improvements is a command for Claude Code from amusleh-spotware-com/terse-sharp. It costs 46 tokens per session (5,704 once invoked), scanned A, original, MIT.

A command that implements every open improvement in a project, updates its documentation, verifies the work, and releases the result to NuGet, a package registry for .NET software.

In plain words
What is it for?
Completing improvement items, updating records, running checks, committing and pushing changes, waiting for CI, and publishing a .NET package release.
Why use it?
It takes a list of unfinished improvements through implementation, testing, continuous integration, release, and publication.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions Claude Code.

This is amusleh-spotware-com/terse-sharp's own configuration. It tells Claude Code how to work on terse-sharp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything terse-sharp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to amusleh-spotware-com/terse-sharp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/amusleh-spotware-com/terse-sharp/main/.claude/commands/ship-improvements.md
Clone the repo
git clone --depth 1 https://github.com/amusleh-spotware-com/terse-sharp

Made for: Claude Code.

Wrote 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.

agentmods badge for ship-improvements

README.md
[![agentmods](https://agentmods.dev/badge/commands/amusleh-spotware-com/terse-sharp/ship-improvements/github.svg)](https://agentmods.dev/commands/amusleh-spotware-com/terse-sharp/ship-improvements)
Your own site
<a href="https://agentmods.dev/commands/amusleh-spotware-com/terse-sharp/ship-improvements"><img src="https://agentmods.dev/badge/commands/amusleh-spotware-com/terse-sharp/ship-improvements/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.

agentmods 80×15 button for ship-improvements

Your own site · 80×15
<a href="https://agentmods.dev/commands/amusleh-spotware-com/terse-sharp/ship-improvements"><img src="https://agentmods.dev/badge/commands/amusleh-spotware-com/terse-sharp/ship-improvements.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,704 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.05704
Opus 5.5 $0.00018 $0.02282
Sonnet 5.5 $0.00009 $0.01141
Haiku 4.5 $0.00005 $0.00570

Measured 20d ago against content hash 74ff8d42ee03, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ship-improvements scanned grade A with 1 finding 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 20d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -s https://api.nuget.org/v3-flatcontainer/tersesharp/index.json`
.claude/commands/ship-improvements.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🚫 HARD GATE — every open row leaves ## Open in THIS run

$ARGUMENTS — if it parses as X.Y.Z, that is the release version; otherwise it is ignored and the version is derived in P6. Nothing else in this command takes input from the user.

Banned for the whole run, without exception:

  • AskUserQuestion, ExitPlanMode, "shall I continue?", a summary that hands work back.
  • Stopping at the first failure. A red build, a red test, a red CI leg, a rejected edit, a failed release job is an input to the next step, not an exit. Diagnose, fix, re-verify, continue.
  • Declaring a phase done that was not run. If a phase genuinely cannot execute, run the strongest substitute, say so in the final report as DEGRADED with the reason, and continue.
  • Skipping a row because it looks hard, vague or unmeasurable.
  • Read / Grep / Glob / Edit / Write on anything under this repo, and Bash: git status, git diff, git log, grep, rg, cat, head, tail, sed, awk, ls, find, dotnet build, dotnet test, dotnet clean, dotnet format (one carve-out, P4.3). Every one of those is a terse-sharp call. Only git blame, index/history mutation (add, commit, tag, push), gh, and the NuGet probe stay on Bash.
  • A blind wait. Every wait on an external process detects the process dying, not only the artifact appearing (P8, P10, P11 give the exact shape).
  • git add -A / git commit -am. Stage by path.
  • A Co-Authored-By: trailer in any commit message.
  • Weakening, skipping or deleting a test to make a suite go green.

Banned reasoning — these were the measured causes of a partial run, and each is false:

"this cannot be completed to standard in one pass" · "I'll ship what's done and open a follow-up" · "the remaining rows are large" · "context is filling up" · "let me read this file first to understand the area" · "one row at a time is safer" · "I'll report honestly instead of finishing".

A previous run closed 13 of 29 rows in ~150 tool calls — 11.5 calls per row — because it worked depth-first and sequentially, reading whole files to "understand" each area before editing. The rows are almost entirely independent and touch disjoint files. P1 below removes that failure mechanically: the investigation fans out in parallel, the applying stays serial, and no row is investigated by the main thread. There is no capacity argument left to make.


Read the full file on GitHub · 340 lines

Changes

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.

  1. 20d ago Changed · +9 lines 74ff8d42ee03
  2. 23d ago Changed · +6 lines 5208267432b4
  3. 28d ago Changed · +9 lines c8b6a3a99122
  4. 1mo ago Changed · +3 lines 1d688f6f9c83
  5. 1mo ago Changed · -30 lines · +2 tokens per session 0f2a37af6e16
  6. 2mo ago First seen · 343 lines · 44 tokens per session scan A 622a7e1aeea0

Subscribe to this mod's changes

ship-improvements is a command published in the GitHub repository amusleh-spotware-com/terse-sharp (3 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 5,704 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.