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 larcane97/clausona --skill fleet-coregit clone --depth 1 https://github.com/larcane97/clausonaWrote 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/larcane97/clausona/fleet-core)<a href="https://agentmods.dev/skills/larcane97/clausona/fleet-core"><img src="https://agentmods.dev/badge/skills/larcane97/clausona/fleet-core/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/larcane97/clausona/fleet-core"><img src="https://agentmods.dev/badge/skills/larcane97/clausona/fleet-core.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 | $0.00053 | $0.04437 |
| Opus 5.5 | $0.00021 | $0.01775 |
| Sonnet 5.5 | $0.00011 | $0.00887 |
| Haiku 4.5 | $0.00005 | $0.00444 |
Grade B, and why
fleet-core scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.codex/config.toml`. Then `CODEX_HOME`, and the variables a runner sets in its terminals such How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleet rules shared by every runner
A fleet is one main session (Claude Code or Codex) that splits work into tasks and runs each task as
a worker: a separate Claude Code or Codex session in its own git worktree, on a clausona profile. A
profile is one account or one API endpoint, with its own sign-in and limits. Profiles of one tool
share plugins and settings. csn is short for clausona.
The runner skill that loaded this one (Superset, herdr, Orca or tmux) says how to create worktrees, start workers, read them and remove them. This skill says everything else.
Shells. Commands here are written for a POSIX shell. Claude Code runs them in Bash, on Windows
too (Git Bash). Codex on Windows runs PowerShell: there, read "$(cat <file>)" as
(Get-Content -Raw <file>), $(command -v clausona) as (Get-Command clausona).Source, and
<cmd> </dev/null as $null | <cmd>. ~ is your home
directory: %USERPROFILE% on Windows. The shell can be zsh, which does not split an unquoted
variable into words: loop over paths written out one by one, not over a variable holding several.
Hidden variables in Codex. A Codex config can pass your commands only a few environment
variables: [shell_environment_policy] with inherit = "core" or "none", usually in
~/.codex/config.toml. Then CODEX_HOME, and the variables a runner sets in its terminals such
as herdr's HERDR_*, look unset even when they are set. When one you need is unset in Codex, look
for that setting. If it is there, tell the user: the fix is to start this Codex session again with
-c shell_environment_policy.inherit=all added to its command, which changes that session only.
1. Profiles and the main session
clausona list --json lists the profiles.
- Every profile has
name,tool(claudeorcodex) andconfigDir. - A subscription profile has
quota.state,quota.session.usedPercent(5H) andquota.weekly.usedPercent(7D). It can also havequota.scoped: the most used window of a limit on one model, named in itslabel. Claude's are weekly; a Codex one can be its 5-hour window, andwindowSecondssays which. - An API profile has
kind: "api"andmodelinstead. These exist for Claude Code only.
What ships with it
1 file 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.
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.
- 9d ago Changed · +24 lines · +5 tokens per session 4276d5904d6c
- 12d ago Changed · +1 lines f8744f2c961f
- 16d ago First seen · 285 lines · 48 tokens per session scan B ee750ab8519d
fleet-core is a skill published in the GitHub repository larcane97/clausona (57 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 4,437 once invoked, about $0.0002 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 2026-10-10.
Other skills, from other repositories
autofix-pr
Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
docs-update-from-diff
Review local code changes with git diff and update the official docs under docs/ to match. Use when the user asks to document current uncommitted work, sync docs with local changes, update docs after a feature or refactor, or when phrases like "git diff", "local changes", "update docs", or "official docs" appear.
prepare-pr
Prepare GitHub pull request title and body files from the current branch diff, especially for non-interactive CI/autofix flows that must follow the repository PR template without pushing or creating the PR.
triage
Gatekeep and review GitHub issues and pull requests for Qwen Code maintainers. Use for GitHub Action issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments.