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.
git 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/battery)<a href="https://agentmods.dev/commands/dwarvesf/dwarves-kit/battery"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/battery/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/dwarvesf/dwarves-kit/battery"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/battery.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 | $0.00063 | $0.03191 |
| Opus 5.5 | $0.00025 | $0.01276 |
| Sonnet 5.5 | $0.00013 | $0.00638 |
| Haiku 4.5 | $0.00006 | $0.00319 |
Grade B, and why
battery scanned grade B 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
For a PR target, find a local checkout of that repo under `~/workspace/<owner>/<repo>`, or any `git worktree list` entry already on the head branch. If no worktree holds the head branch, stop and tell the lead to create How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running the verification battery on a finished build (a branch, a PR, or the active spec's diff). The build's own orchestration already ran; your job is the INDEPENDENT right arm: fresh-context agents that did not write the code, re-executing and re-reading it. Never "review" inline in the session that wrote the code and call it the battery.
Scope and triggers
The multi-lens review runs single-pass minimum, with domain lenses on escalation. This battery exists because independent arms catch DISJOINT defect classes: on one measured diff the panel, the reviewer, the verifier, and a late security lens each found a defect the other three missed.
Bracket the phase for timing, after the Size gate below passes and before dispatching any arm: bash lib/gate/gate-ledger.sh outcome <rid> battery start (rid = the branch slug, the same key the ship-gate reads; the ledger counts battery as the review gate). For a foreign target the ledger writes under the run dir of the cwd repo, not the target repo. Run the two gate-ledger.sh calls from the target repo's primary checkout root in a subshell ((cd <repo> && bash ...)), or accept the record landing under the session repo.
Target (optional argument)
Resolve the target FIRST, before the size gate, the bracket and any dispatch.
| Argument | Resolves to |
|---|---|
| none | the cwd repo, its current branch, compare ref origin/<default branch> |
| a worktree or repo path | that checkout's branch, its repo's default branch as compare ref |
owner/repo#N or a PR URL |
gh pr view N -R owner/repo --json headRefName,baseRefName,headRefOid; compare ref is the PR base |
Read a repo's default branch from git -C <path> symbolic-ref --short refs/remotes/origin/HEAD.
For a PR target, find a local checkout of that repo under ~/workspace/<owner>/<repo>, or any git worktree list entry already on the head branch. If no worktree holds the head branch, stop and tell the lead to create one at <repo>/.claude/worktrees/<slug> on that branch before dispatching. Never branch-switch a primary checkout.
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.
- 7d ago Changed · +2 lines 3f29b5fd62dd
- 22d ago Changed · +11 lines 134a6932198b
- 24d ago Changed · +65 lines df5a40d593f7
- 25d ago Changed 9d5c88728cff
- 1mo ago Changed · +4 lines · -45 tokens per session 27680d1ed631
- 1mo ago Changed 70364d8f03c7
- 1mo ago Changed · +49 lines scan A → B 101b3fbbea8e
- 1mo ago Changed · +3 lines 06a0ec861631
- 1mo ago First seen · 75 lines · 108 tokens per session scan A cb5e37d9d6e6
battery is a command published in the GitHub repository dwarvesf/dwarves-kit (12 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 3,191 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other commands, from other repositories
kiro-validate-impl
Command "kiro-validate-impl" from gotalab/cc-sdd, covering implementation validation, core task, execution steps, 1. detect validation target and 2. load context.
spec-completion-review
Spec completion review - verify implementation matches spec.
speckit.companion.living-coverage
Report living-spec requirement→test coverage — per requirement, whether its coverage tier maps a test (opt-in, read-only, never halts).
sddp-qc
Command description: Run quality control against the implemented feature. Argument hint: [optional: testing focus such as unit tests, security audit, requirements sync] Command category: feature-delivery Prerequisites: spec, plan, tasks, implementation:complete.
refactor
Refactor and optimize [code].
review.speckit-test
Review the test automation implementation against the specification and the desired test pyramid shape; detect and explain misalignment - prioritise unit tests, identify high-value gaps and brittle tests, and provide actionable recommendations (including refactoring) to improve behavioural confidence.