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/shiyas1331/devkit/splitgit clone --depth 1 https://github.com/shiyas1331/devkitWhat 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 | $0.00040 | $0.12427 |
| Opus 5 | $0.00020 | $0.06214 |
| Sonnet 5 | $0.00008 | $0.02485 |
| Haiku 4.5 | $0.00004 | $0.01243 |
Grade A, and why
split 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 yesterday.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
blob = subprocess.run( How it starts
The opening of the file, as written. The whole thing — 1,338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Split a large set of changes into smaller dependency-aware PRs
Large changesets are slow to review and easy to merge with bugs. This command analyzes either an open PR OR a local branch, identifies logical groupings, computes import-based dependencies between them, and produces a concrete split plan.
Two input sources:
- PR mode — point at an open GitHub PR (URL, number, or its branch
name). Files come from
gh api. - Local mode (
--local/--branch=<name>) — point at a local branch that hasn't been pushed yet. Files come from `git diff
Three execution modes:
- SUGGEST (default) — analysis only. Outputs a split plan, a reviewable shell script, and draft PR descriptions. No side effects.
- DRAFT (
--draft) — runs SUGGEST first, then creates the actual git branches locally (one per bucket). Does NOT open PRs. - EXECUTE (
--execute) — runs SUGGEST + DRAFT, then opens GitHub PRs for each branch in dependency tier order. Each PR uses the draft description from Phase F. Stacked PRs get the right--base. In local mode, EXECUTE requires the original branch to be pushed first (refuses with a clear message if not).
Response format: one short sentence on what was done, the next concrete action, terse.
Mode picker (front door for empty invocations)
Front door A — picker fires by default
Trigger:
$ARGUMENTSis empty, OR$ARGUMENTScontains only a PR identifier with no--*flag
Step 1 — choose the source. Use AskUserQuestion:
question: "What are you splitting?"
header: "Source"
multiSelect: false
options:
- label: "An open GitHub PR"
description: "Point at an existing PR — by URL, number, or its
branch name. Files are fetched via `gh api`. Use
this when the PR is already open and you want to
break it down."
- label: "A local branch (not yet pushed / no PR yet)"
description: "Split your current branch (or a named branch) BEFORE
opening a single mega-PR. Files come from `git diff
<base>...HEAD`. The best time to split — analyze
your work before review surface exists."
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.
- yesterday First seen · 1,338 lines · 40 tokens per session scan A 58a0317d463c
split is a command published in the GitHub repository shiyas1331/devkit (4 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 12,427 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.