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 unleashgit 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/unleash)<a href="https://agentmods.dev/skills/rafael-adcp/kraken/unleash"><img src="https://agentmods.dev/badge/skills/rafael-adcp/kraken/unleash/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/unleash"><img src="https://agentmods.dev/badge/skills/rafael-adcp/kraken/unleash.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 | $0.00094 | $0.03386 |
| Opus 5 | $0.00047 | $0.01693 |
| Sonnet 5 | $0.00019 | $0.00677 |
| Haiku 4.5 | $0.00009 | $0.00339 |
Grade A, and why
unleash 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 12d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kraken — one head, many tentacles
You are a tentacle: a named worker draining the task queue in the kraken's head — my coordination repo, a private repo whose GitHub Issues ARE the tasks. Work repos can live anywhere (GitHub, GitLab, private servers) — each issue says which project it belongs to.
You do not have to remember the protocol. kraken.py next-action tells you what to
do next, every time, and hands you the exact commands to run. Whether you already hold a
task, whether your lease is still yours, when to renew it, which writes are legal — all
of that is the program's job. Yours is the judgment: read the goal, write the code, ask
the blocking question, report the real result.
The coordination contract — task shape, the kraken-task / in-progress /
needs-decision / awaiting-merge state machine, the claim algorithm, the machine
marker, authorization boundaries — is normatively specified in
PROTOCOL.md (kraken-protocol/9). If this file and the spec ever
disagree, the spec wins.
Invocation
/kraken:unleash OWNER/tasks --worker-name <alias> --project <name> [--once]
The first three arguments are REQUIRED. If any is missing, do not start — ask for
it. 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.
--worker-name: this worker's identity, carried in every claim and comment. Every worker authenticates as the same user, so the name is the only thing that tells tentacles apart in the audit trail. Pick names that say where the work ran.--project: only take tasks labeledproject:<name>, because a worker runs in an environment prepared for a specific project.--once(optional): drain the queue once and stop, instead of staying in ambush.
You work ONE task at a time. Capacity is how many workers I launch, never how many tasks one worker juggles. The program enforces this; do not work around it.
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- DELIVERY.md 3.0 KB
- kraken.py 1.7 KB runs code
- kraken/__init__.py 5.5 KB runs code
- kraken/claim.py 32 KB runs code
- kraken/cli.py 12 KB runs code
- kraken/comments.py 5.4 KB runs code
- kraken/contract.py 9.3 KB runs code
- kraken/lease.py 15 KB runs code
- kraken/next_action.py 30 KB runs code
- kraken/queue.py 28 KB runs code
- kraken/reconcile.py 18 KB runs code
- kraken/refs.py 18 KB runs code
- kraken/render.py 8.5 KB runs code
- kraken/state.py 19 KB runs code
- kraken/status.py 11 KB runs code
- kraken/terminal.py 9.1 KB runs code
- kraken/transport.py 20 KB runs code
- kraken/watch.py 6.4 KB runs code
- kraken/workflow.py 16 KB runs code
- task-template.yml 1.6 KB
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.
- 12d ago First seen · 240 lines · 94 tokens per session scan A 188d59f4bb95
unleash is a skill published in the GitHub repository rafael-adcp/kraken (4 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 3,386 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
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.
vibe-status
Use when you want a snapshot of all active vibe-kanban workspaces, their PRs, and any inconsistencies - shows dashboard-style table with workspace state, branch, PR status, CI, and review state, flags anything stuck or inconsistent.
matilha-hunt
Use when user is ready to dispatch a wave's subprojects — creates git worktrees and kickoff.md per SP, writes wave-NN-status.md, prints dispatch commands.
recursive-spine-method
Use when a builder wants to learn or be reminded of the recursive-spine tracking convention — where work state lives (GitHub issues+milestones, never prose ledgers), the five principles, the module system, and how to design a repo's dialect. Pure knowledge; takes no actions.
recursive-spine-migrate
Use when converting a repo's existing prose work-ledgers (status files, queue tables, gap/debt registers, follow-up files, deferral tails) into GitHub issues and milestones under the recursive-spine convention. Dry-run by default — inventories and proposes, writes nothing. Live mode files issues with back-links and…
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.