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/dwarvesf/dwarves-kit/nextgit clone --depth 1 https://github.com/dwarvesf/dwarves-kitWhat 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 | $0.00023 | $0.01020 |
| Opus 5 | $0.00012 | $0.00510 |
| Sonnet 5 | $0.00005 | $0.00204 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
next 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a task dispatcher. Read the spec, find the next task to work on, and set up the context for implementation.
Process
Step 1: Find the next task
Read the active spec. Resolve it the same way the hooks do (the SPEC-005 dual-mode rule, reconciled to ADR-0010): among docs/specs/SPEC-*.md, take the lone non-SHIPPED/PARKED spec; if several are live, pick the one whose slug matches the current git branch; if the branch match is zero or ambiguous, ask the user which spec (do NOT guess). docs/specs/SPEC-NNN-<slug>.md is the sole spec location (ADR-0010).
Find the first task that is:
- Not marked as done (
[x]orDONE) - Has all dependencies satisfied (dependent tasks are done)
If multiple tasks are available (independent, no ordering constraint), present them and let the user pick.
Step 2: Load context
For the selected task, gather:
- The task description and acceptance criteria from the spec
- Relevant files mentioned in the task or in
docs/briefs/CONTEXT.md - Current git branch and status
- Any related decision records from
docs/decisions/
Step 3: Present the task briefing
## Next task: TASK-[ID]
[description]
### Acceptance criteria
- [ ] [criterion 1]
- [ ] [criterion 2]
### Files to touch
- [file 1] — [what to change]
- [file 2] — [what to change]
### Context loaded
- [relevant file or decision]
### Dependencies
- TASK-[X]: [done/pending]
### Remaining after this
- [N] tasks left in current phase
- [N] tasks left total
Step 4: Hand off
Say: "Ready to implement. Work through the acceptance criteria one by one. When done, run /kit:next again for the next task, or /kit:review to review your changes."
Also remind: "As you implement, maintain docs/implementation-notes/<spec-slug>.md. Append an entry whenever you make a decision the spec did not pin down, deviate from the spec, hit a tradeoff worth surfacing, discover a missing constraint, or hit an open question you'd want the operator to confirm or revise. Entry shape: ## YYYY-MM-DD HH:MM <title> with Context / Decision / Why / Alternatives considered / Impact / Open questions lines. If TASK-[ID] runs with zero deviations, append a one-line TASK-[ID]: no deviations; matches <spec> verbatim entry so the absence is intentional. The file is surfaced in the /wrap-session LAB_LOG line and the PR description."
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.
- 2d ago First seen · 75 lines · 23 tokens per session scan A c5589cabe4fb
next is a command published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,020 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
OPSX: Archive
Archive a completed change in the experimental workflow.
OPSX: Explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.
OPSX: Sync
Sync delta specs from a change to main specs.
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Update
Update a change - revise existing planning artifacts and keep them coherent (Experimental).