Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add dsnger/dev-workflow-kit/plugin install dev-workflowWrote 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/dsnger/dev-workflow-kit/claude-init)<a href="https://agentmods.dev/commands/dsnger/dev-workflow-kit/claude-init"><img src="https://agentmods.dev/badge/commands/dsnger/dev-workflow-kit/claude-init/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/dsnger/dev-workflow-kit/claude-init"><img src="https://agentmods.dev/badge/commands/dsnger/dev-workflow-kit/claude-init.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 | $0.00021 | $0.03912 |
| Opus 5.5 | $0.00008 | $0.01565 |
| Sonnet 5.5 | $0.00004 | $0.00782 |
| Haiku 4.5 | $0.00002 | $0.00391 |
Grade A, and why
claude-init 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 21d 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.
How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write a CLAUDE.md of general working rules into the current project: think before coding,
simplicity, surgical changes, goal-driven execution, and not guessing. This is the lighter entry
point beside /dev-workflow:workflow-init — it installs no review gates and writes no other file.
Target model: Claude via Claude Code. This command is a prompt artifact and follows
the dev-workflow prompt checklist (docs/prompt-standards.md in the dev-workflow-kit repository).
Context
- The only file this command writes is
CLAUDE.md, in the current directory. No marker, no README note, noAGENTS.md, no.context/, no commit — the user asked for one file, and every extra file is something they did not ask to own. - It needs nothing a directory does not have, with one exception. No git repository, no plugin, no MCP server, no package manager. Reading and proposing work anywhere. Creating the file needs a Python 3 that is already installed, because that is where the one safe create operation lives (see Writing). Where it is missing, the command stops instead of writing some weaker way.
- It is an entry point, never an exit. Where a
CLAUDE.mdalready carries review gates — aCross-Model Reviewsection, Gate A / Gate B — they stay exactly as they are. This command never removes, disables, weakens or renumbers a gate, because a project that has gates chose them.
Done means
- Exactly one report state from Report below was printed, and it describes what you observed, not what you expected.
- At most one file changed on disk:
CLAUDE.md, and only when it did not exist before. - An existing
CLAUDE.mdis byte-for-byte what it was before the command ran.
Step one — what kind of path is CLAUDE.md?
Ask this before looking at any content: a path that cannot be classified safely must never reach a content decision. Run:
ls -ld CLAUDE.md
test -L CLAUDE.md && echo symlink
test -r CLAUDE.md && echo readable
Test for a symlink first. test -e and test -f follow links, so a dangling link would read as
"absent" and the create would write through it into another place.
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.
- 21d ago First seen · 292 lines · 21 tokens per session scan A 314daa81c2a7
claude-init is a command published in the GitHub repository dsnger/dev-workflow-kit (6 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 3,912 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 2026-09-26.
Other commands, from other repositories
plan
Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.
init
Install the formatters this repository needs, with every command visible before it runs.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
audit
Onboard an existing codebase: every domain's checks over the whole tree, then a triaged plan to bring it in line.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
test
Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green.