Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dwarvesf/dwarves-kitnpx agentmods add commands/dwarvesf/dwarves-kit/wrapWrote 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/dwarvesf/dwarves-kit/wrap)<a href="https://agentmods.dev/commands/dwarvesf/dwarves-kit/wrap"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/wrap.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 5.1 | $0.00147 | $0.03529 |
| Opus 5 | $0.00073 | $0.01765 |
| Sonnet 5 | $0.00029 | $0.00706 |
| Haiku 4.5 | $0.00015 | $0.00353 |
Grade A, and why
wrap 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 today.
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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-intro (AGENTS.md "Self-intro" convention): open your first reply with exactly one banner line, [kit:wrap] Land the session after ship: board rows, merges, deploy check, tidy, activity line, retro., then proceed.
You are the session's landing step. The operator just shipped, or is ending the session, and nothing in the kit lands that session on its own: board rows stay unflipped, the operator's own green PRs stay unmerged, a merged-but-undeployed PR goes unnoticed, branches and worktrees pile up, and /kit:retro never runs. Your job is one pass over every repo the session touched, closing out every step below in order.
When this runs
- After
/kit:shipcompletes, for the repo that just shipped. - At the end of a session, before the operator closes the terminal.
- Whenever the operator asks to land, wrap up, or close out the session.
- Never mid-build: a spec still mid-execute has nothing to land yet.
Prerequisites
- Each named repo (or the current repo, when none is named) is a git repository. A non-repo argument prints a skip line and the rest proceed.
ghis optional. When it is absent or unauthenticated, every branch that is not a plain ancestor of the default branch verdictsunknown: LEAVEandbin/wrap mergerefuses with exit 1; the command still runs the other seven steps and reports the degraded state, it never stops for this reason alone.
Process
Bracket the phase for timing (SPEC-129) before starting: bash lib/gate/gate-ledger.sh outcome <rid> wrap start.
Run the steps below once per repo the session touched (the current repo when the operator names none). Positional repo arguments; wrap never discovers touched repos on its own (Out of Scope).
Step -1: the before seam
An operator can put one skill in front of this command. Read the key first:
. lib/config/kit-config.sh && kit_config_get_root wrap.before ""
An empty value means no skill runs, which is the default; go straight to step 0. A named skill runs NOW, before step 0, and its report lines fold into step 9's report after the FYI line. The key resolves with kit_config_get_root, so it comes from the operator kit.toml or the kit-root kit.toml and never from a project .kit.toml: it names code this command runs, and a project toml rides inside an untrusted PR.
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.
- today First seen · 154 lines · 147 tokens per session scan A a6240925c789
wrap is a command published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed yesterday), licensed MIT. It adds 147 tokens to every session and 3,529 once invoked, about $0.0007 per session on Opus 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 2026-09-07.
Other commands, from other repositories
release
Verify, sweep docs, cut a version — then hand the release sequence back.
pr-package
Prepare a clean delivery package for GitHub from the real git diff vs an explicit base branch, persisted as PRPACKAGE.md (or PRPACKAGE. .md for multi-repo tasks). Produces branch name, commit messages, fetch, checkout, add, commit, and push commands, PR title and body, and reviewer attention points; never invents work…
release-isparto
You are the Team Lead. The user has run /release-isparto to publish a new version.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.
sddp-implement
Command description: Implement the current feature tasks. Argument hint: [optional: phase or task to start from] Command category: feature-delivery Prerequisites: spec, plan, tasks, checklists:complete-if-present.
finish-branch-execute
Step 4 of finishing-a-development-branch: Execute chosen integration option (merge, PR, PR+dance, keep, or discard).