agentmods.dev

init

An installer and setup command for turning a repository into a worklog repository. It adds the required work-tracking files, hooks, configuration, and continuous-integration setup.

In plain words
What is it for?
Use it when first installing worklog or upgrading an existing installation, then configuring connections to systems such as GitHub, GitLab, Jira, Linear, or a wiki.
Why use it?
It prepares the repository for visible work tracking and identifies the team's ticketing and documentation systems, reducing manual setup.

Command

10 3d ago A scan 44 tokens original MIT
View the source file SpillwaveSolutions/wiki_ticket_sdd
Install

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.

agentmods
npx agentmods add commands/spillwavesolutions/wiki_ticket_sdd/init
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/wiki_ticket_sdd
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 922 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.00922
Opus 5 $0.00022 $0.00461
Sonnet 5 $0.00009 $0.00184
Haiku 4.5 $0.00004 $0.00092

Measured 2d ago against content hash 3f992f618d9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

plugin/commands/init.md · 49 lines

What it actually says

Install (or upgrade) worklog in the current repo:

  1. From the repo root, run:

    bash "${CLAUDE_PLUGIN_ROOT}/scripts/init.sh"

  2. Show the user the script's output (version installed, what was written vs skipped, upgraded-from if applicable).

  3. Detect the repo's systems — but first check .work/config.yml: if its ticketing: and wiki: blocks already name real systems (not the template defaults), this is an upgrade re-run — SKIP detection entirely, do not re-ask, go to step 8. Otherwise gather evidence:

    • git remote -v — map hostnames to platforms: github.com → GitHub (Issues, PRs, wiki); gitlab → GitLab; dev.azure.com / visualstudio.com → Azure DevOps; codecatalyst.aws → AWS CodeCatalyst; bitbucket → Bitbucket. Trackers with no git hosting (Linear, Jira) never show in remotes — CLI/MCP evidence is how they surface.
    • command -v gh glab az jira acli aws linear — which platform CLIs are installed. For the remote's platform CLI, check auth (e.g. gh auth status).
    • MCP tools available in this session — a Jira/Confluence/Linear/Notion MCP is evidence the team uses that system.

  4. Confident case. If tickets, PRs, and wiki are all confidently determined (e.g. a single github.com origin and gh is authenticated), present ONE short summary and ask a single yes/no via AskUserQuestion:

    Detected: GitHub Issues for tickets, GitHub PRs, GitHub wiki — correct?

  5. Unsure case (mixed signals, no remote, or the user said no): AskUserQuestion per area, multiSelect on, so teams can pick and mix (GitHub PRs + Jira tickets + Confluence wiki is a legal combination):

    • Tickets: GitHub Issues, GitLab, Azure DevOps, Jira, Linear, AWS CodeCatalyst, other
    • Wiki: GitHub wiki, GitLab wiki, ADO wiki, Confluence, other, none

    other is a real answer, not a shrug: write system: other plus the actual system name in options:, and the sync/publish skills resolve tooling at runtime. (GCP has no native tracker — GCP-hosted teams land on one of the above.)

  6. Write the answers into .work/config.yml by editing the existing ticketing: and wiki: blocks in place — set system, and fill project / root_url from what's known (remote URL, org/repo). Keep the file's comments intact.

  7. Offer the work-taxonomy block. Show the user the taxonomy block (the canonical text is the heredoc in scripts/init.sh — four axes, six rules, inline-proposal policy), then AskUserQuestion yes/no: "Teach the work taxonomy in CLAUDE.md?" On yes, run:

    bash "${CLAUDE_PLUGIN_ROOT}/scripts/init.sh" taxonomy

    This writes ONLY the block, between <!-- worklog:taxonomy:start/end --> markers, idempotently — re-running updates in place, never duplicates. Plain init.sh never touches it: CLAUDE.md is not silently rewritten. Because AGENTS.md symlinks to CLAUDE.md, Codex/Grok/OpenCode inherit the block for free.

  8. Run git status, review the scaffolding it added or updated, and commit it all — scaffold plus config — in ONE commit (e.g. worklog: scaffold repo (plugin v0.1.0)). The copies are committed deliberately so git hooks and CI work for teammates who do not have the plugin.

The script is idempotent: re-running on an installed repo is the upgrade path. It never touches existing .work/*.jsonl logs.

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. 2d ago First seen · 49 lines · 44 tokens per session scan A 3f992f618d9e

Subscribe to this mod's changes

init is a command published in the GitHub repository SpillwaveSolutions/wiki_ticket_sdd (10 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 922 once invoked, about $0.0002 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 2026-08-31.

Git and workflowProject management
Related

Other commands, from other repositories

git

Git operations with intelligent commit messages and workflow optimization.

SuperClaude-Org/SuperClaude_Framework · 11 tokens

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

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.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens

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.

github/spec-kit · 35 tokens