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 skills add dwarvesf/dwarves-kit --skill statsgit 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/skills/dwarvesf/dwarves-kit/stats)<a href="https://agentmods.dev/skills/dwarvesf/dwarves-kit/stats"><img src="https://agentmods.dev/badge/skills/dwarvesf/dwarves-kit/stats.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 5.1 | $0.00367 | $0.01983 |
| Opus 5 | $0.00183 | $0.00992 |
| Sonnet 5 | $0.00073 | $0.00397 |
| Haiku 4.5 | $0.00037 | $0.00198 |
Grade A, and why
stats 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 3d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stats
Read-only, agent-callable observability over the ledgers dwarves-kit and its
neighbors (tide, tg-cleanup, learned-ledger) already write. The tool dir is
~/workspace/<owner>/dwarves-kit/lib/stats (run uv run stats <cmd>
there). Everything is read-only: the CLI never writes back to a source ledger; there
is no path through this skill that mutates anything.
One data path: always query via the stats CLI
Never re-derive a ledger reading by grepping ~/.local/state/dwarves-kit/logs/ or
tide's sqlite or tg-cleanup's json yourself , that is a second, divergent data
source and breaks the whole point of the lens (SG-02 already reuses lane-telemetry
for the kit read; re-implementing it here would drift). Always go through stats.
Which command answers which question
| The operator wants | Command |
|---|---|
| "show me the ledger state" / "kit runs" / "kit lane telemetry" | stats render kit_runs --surface terminal |
| "my debt" / "understanding debt" | stats anomalies (checks SUM(kit_runs.gates_ovr) against threshold; this is the current debt signal, superseding a raw grep over | DEBT | lines). For the raw numbers behind it, stats query "SELECT rid, gates_ovr FROM kit_runs WHERE gates_ovr > 0" --surface terminal |
| "any ledger anomalies" / "should I propose anything" | stats anomalies (report only) or stats anomalies --propose (stage a candidate row per fired anomaly into the cc-backlog staging buffer; never files a board row) |
| "telemetry" (tide moves) | stats render tide_moves --surface terminal |
| "token cost" / "how much am I spending on tokens" | stats render tide_tier_b_calls --surface terminal (per-call cost/token rows); for a spike check specifically, stats anomalies |
| "ledger status" / a quick glance at everything | stats tables first (row counts per table), then render the table the operator actually cares about |
| "render the ledger" / "ledger dashboard" / "share this as an artifact" | the same render command with --surface artifact --out <tmp path>.html, then call the Artifact tool on that file |
| an ad-hoc cross-ledger question ("which runs correspond to which tide moves") | stats render --query "<read-only SQL JOIN>" --surface terminal |
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.
- 3d ago First seen · 112 lines · 367 tokens per session scan A 4d1e39cc7b26
stats is a skill published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed today), licensed MIT. It adds 367 tokens to every session and 1,983 once invoked, about $0.0018 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 skills, from other repositories
what-next
Determine the current stage of the active task and recommend the single best immediate next command, editor mode, and work complexity. Routes based on TASKSTATE.md, DECISIONS.md, and IMPLEMENTATIONPLAN.md without reopening broad discovery. Use when the user wants a fast operational answer for what to do next, when the…
nil
The inverse of /sfl. Where sfl saved each window for later, /nil says later is now: it reopens them. You choose which to bring back.
headsup-config
Unified settings hub for headsup (Claude Code's iTerm2 status hooks). One command with a section as the first word, then that section's args. Sections: newtabs (New Claude Tab / Cmd-Opt-C launch mode), colors (idle/processing/waiting tab colors), label (this tab's title + badge), notify (the 'Claude is waiting' macOS…
sfl
Save For Later: checkpoint this window so a fresh session (or /nil) can resume it later. Use when the user types /sfl, "save for later", or "checkpoint this window". Writes a live per-window entry under /.claude/sfl/ (plus an optional durable note in the user's own memory system), then shows the green Saved-for-Later…
headsup-colors
Customize headsup's global iTerm2 tab colors for Codex sessions: idle, working, and waiting. Use when the user asks to change Codex/headsup tab colors.
headsup-notifications
Manage macOS notifications for Codex tabs that have been waiting longer than a configured threshold.