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/verifygit clone --depth 1 https://github.com/dwarvesf/dwarves-kitWrote 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/verify)<a href="https://agentmods.dev/commands/dwarvesf/dwarves-kit/verify"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/verify.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 | $0.00046 | $0.03015 |
| Opus 5 | $0.00023 | $0.01507 |
| Sonnet 5 | $0.00009 | $0.00603 |
| Haiku 4.5 | $0.00005 | $0.00301 |
Grade A, and why
verify 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only verifier. Your job is to re-run the V-model right arm's test levels against the current spec and branch WITHOUT rebuilding and WITHOUT changing the code under test. You report a verdict; you never fix. The one thing you DO write is the verification record itself (an append to docs/verification/<spec-slug>.md) , recording that a run happened is the point of the command, not a change to the artifact under test.
This is the on-demand counterpart to the verification /kit:execute runs inside its build loop, plus the two right-arm levels /kit:execute does not cover: same agents (task-verifier, integration-verifier, acceptance-verifier, system-verifier), no worker, no fix-agent. Use it after a manual edit, on a branch built elsewhere, or when the /goal loop needs a read-only check.
Prerequisites
- A spec exists at
docs/specs/SPEC-NNN-<slug>.md(or passSPEC-NNNas the argument). - There is committed (or working-tree) code to verify.
If no spec exists, say so, list the specs under docs/specs/, and stop. Do not invent one.
Process
Bracket the phase for timing (SPEC-129) before starting: bash lib/gate/gate-ledger.sh outcome <rid> verify start.
Step 1: Resolve the active spec
If $ARGUMENTS names a SPEC-NNN, use that spec. Otherwise use the highest-numbered non-SHIPPED spec in docs/specs/. If none resolves, stop per Prerequisites.
Step 2: Compute the diff base (for integration-verifier)
Unlike /kit:execute, there is no pre-build base ref recorded. Compute one:
git merge-base HEAD <default-branch>where<default-branch>isorigin/mainif it exists, elsemain, elsemaster.- If that equals
HEAD(you are on the default branch), fall back to the spec's first commit, elseHEAD~1.
This is the base integration-verifier diffs the branch against.
Step 3: Dispatch the unit/task level (read-only)
For each task marked done (- [x]) in the spec's ## Task Breakdown, dispatch the task-verifier subagent (read-only) against that task's acceptance criteria plus the project test suite. Collect each verdict (PASS / FAIL:fixable / FAIL:escalate). If there are no done tasks, note "no completed tasks to unit-verify" and continue.
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 · 178 lines · 46 tokens per session scan A cfccdec90318
verify is a command published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 3,015 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 2026-09-04.
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: Propose
Propose a new change - create it and generate all artifacts in one step.
OPSX: Sync
Sync delta specs from a change to main specs.
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Update
Update a change - revise existing planning artifacts and keep them coherent (Experimental).