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 skills/rafael-adcp/kraken/initnpx skills add rafael-adcp/kraken --skill initgit 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/init)<a href="https://agentmods.dev/skills/rafael-adcp/kraken/init"><img src="https://agentmods.dev/badge/skills/rafael-adcp/kraken/init.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 | $0.00066 | $0.01665 |
| Opus 5 | $0.00033 | $0.00833 |
| Sonnet 5 | $0.00013 | $0.00333 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
init scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
copies match the installed plugin version and work offline. Never `curl` from How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kraken — raise the head
You are the setup step for kraken: given a coordination-repo slug, you make that repo
ready to receive tasks — the private repo exists, the task template is committed,
everything an earlier release installed to be executed there is deleted, and the
state-machine labels are created. Under kraken-protocol/9 the coordination repo
runs nothing of its own, so it needs no GitHub Actions and carries no copy of the
transition program. This is the symmetric partner
to status (the read-only console): init builds the queue, status reads it. You
touch no issues — none read, none written.
Invocation
/kraken:init OWNER/tasks [--project <name>]
The OWNER/tasks argument is REQUIRED — the coordination repo to stand up. 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. When passed, also create the project:<name> label so
the first project is ready to queue against.
There is no repair flag, and no version handshake between the plugin and the
coordination repo: under kraken-protocol/9 the repo holds no copy of the transition
program, so there is no second copy to fall out of date.
Design decisions
- The mechanics live in
kraken.py init, not in this prose. Standing a repo up — verify-or-create it private, install the bundled assets, upsert the canonical labels — is deterministic, zero-judgment work, so it is executed by the bundledkraken.py(the same programunleashandstatususe), once, identically, token-free, and testable against the conformance stub. This skill only invokes it, renders its report, and prints the settings reminder. Same rule that producedclaim-nextandstatus. - Assets ship in the plugin, never fetched from the network.
task-template.ymllives in this plugin'sskills/unleash/folder —kraken.py initreads it from there and commits it via the GitHub contents API. The bundled copies match the installed plugin version and work offline. Nevercurlfromraw.githubusercontent.com. - Idempotent and non-destructive by construction.
kraken.py initcreates the repo only if absent, creates each asset only if absent, and upserts the labels with their canonical color/description. An existing file is reportedpresentand left exactly as it is. Re-running is safe. - Nothing installed is executed, so nothing has to stay in sync. The one
asset is an issue form — it shapes a task on the way in and runs no code.
A template the operator tuned is their business, not drift to police, which is
why there is no
--upgrade, no byte comparison and no refusal path. - Re-running init is the migration. A coordination repo stood up by an older release still carries the workflows and the vendored program that release installed; a cron left running against retired semantics keeps mutating labels behind every worker's back. So init DELETES them — gated on kraken's own file header, so something the operator wrote at one of those paths is never destroyed by a bootstrap command.
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.
- 5d ago First seen · 127 lines · 66 tokens per session scan A 08433076e82a
init is a skill published in the GitHub repository rafael-adcp/kraken (4 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,665 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.