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 rafael-adcp/kraken --skill statusgit clone --depth 1 https://github.com/rafael-adcp/krakenWrote 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/rafael-adcp/kraken/status)<a href="https://agentmods.dev/skills/rafael-adcp/kraken/status"><img src="https://agentmods.dev/badge/skills/rafael-adcp/kraken/status/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/skills/rafael-adcp/kraken/status"><img src="https://agentmods.dev/badge/skills/rafael-adcp/kraken/status.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 | $0.00103 | $0.01977 |
| Opus 5 | $0.00051 | $0.00988 |
| Sonnet 5 | $0.00021 | $0.00395 |
| Haiku 4.5 | $0.00010 | $0.00198 |
Grade A, and why
status 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 8d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kraken — surface the depths
You are the operator's console for kraken: the one read-only view of a coordination
repo. The whole computation lives in kraken.py status — the review queue and the
decision queue (what needs me), what is still in flight (and which of those claims
have gone silent), the one blind spot the state machine has (an awaiting-merge task
whose PR is already merged but whose issue was never closed — the reconcile only watches
claim refs, and a delivered task has none, so these can sit forever), the queue-entry hygiene report (tasks no
worker can start as filed), and the launch recon (which projects live in this queue). You run the subcommand and render
its output. You read the queue; you never touch it.
Invocation
/kraken:status OWNER/tasks [--project <name>]
The OWNER/tasks argument is REQUIRED — the coordination repo whose queue you report
on. Missing? Do not guess. Ask for it and stop.
A slug that is still the doc placeholder (OWNER/..., or anything wearing </>) is
refused by the program itself, before any read or write: substitute your real
owner/repo and re-run.
--project <name> is OPTIONAL here (unlike unleash). A worker needs project
scoping because it runs in a prepared environment; a human checking the queue does not.
With --project, every list is scoped to project:<name>; without it, the whole queue
is reported and the launch recon enumerates every project.
Protocol
Everything deterministic is mechanized in the subcommand (PROTOCOL.md §12) — the queue
fetch, the PR-link parse, the lease-age anchor, the orphan heuristic, and the
project enumeration. Your job is to run it and render the result; there is no gh
orchestration left to do by hand.
-
Run the subcommand. Pass
--project <name>through only if I gave it:skills/unleash/kraken.py status OWNER/tasks [--project <name>]It prints a ready-to-render human console. For a machine-readable snapshot (scripts, cron, a future
statsover the timeline) add--json— see the schema below. The subcommand is read-only: it runsghreads only (the batched GraphQL queue walk, the claim refs and state records plus their commit meta for in-flight worker/lease-age and the delivery link,gh pr viewfor the orphan check,gh label listfor the recon) and never writes. It opens no comment thread at all, whatever the queue's size.
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.
- 8d ago First seen · 150 lines · 0 tokens per session scan A 5302090f0d97
status is a skill published in the GitHub repository rafael-adcp/kraken (4 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,977 once invoked, about $0.0005 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.
Other skills, from other repositories
workspace
Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.
decision-map
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…
merge-review
Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.
unharness
Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.
lead
Use when acting as the factory tech lead: classify work, ask the minimum questions, create tickets, and dispatch without implementing.
to-tickets
Use when breaking a plan into tracer-bullet GitHub issues with blocking edges.