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 melodic-software/claude-code-plugins --skill reachgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/reach)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/reach"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/reach/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/melodic-software/claude-code-plugins/reach"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/reach.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 | $0.00114 | $0.04320 |
| Opus 5.5 | $0.00046 | $0.01728 |
| Sonnet 5.5 | $0.00023 | $0.00864 |
| Haiku 4.5 | $0.00011 | $0.00432 |
Grade A, and why
reach 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 2d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
One procedure for agent-to-agent reach across the fleet. A lane is one Claude Code install with its own sign-in: the WSL distro or native Windows, on each machine. From any lane this reaches every other lane: run a script there, prompt it, query it and wait, message one of its sessions, or start a named session in it.
Prefer the richest lane for the work. WSL is the default agent lane: it has the repos, the toolchain and sshd. Use native Windows only for Windows-only work and Windows-side sessions.
Read ~/.config/fleet/FLEET.md before composing anything. It is rendered per machine and carries
the real aliases, accounts and paths; the commands below are the same commands with placeholders.
Route matrix
Find the row for where you are and where the work goes. <agent> is the headless turn from
Verbs; in a WSL lane it is claude, in a Windows lane <claude-exe>. "Tested" means a
real run of that exact shape; see reference/relay.md for
what each run showed.
| # | From | To | Command shape | Status |
|---|---|---|---|---|
| R0 | any | same lane | Built-in ListAgents / SendMessage. Not this skill |
n/a |
| R1 | WSL | this machine, Windows | cd <win-dir> && <claude-exe> <agent-args> < /dev/null |
tested: script (powershell.exe), list, multi-turn, message a -n receiver |
| R2 | WSL | other machine, WSL | <ssh> <wsl-alias> 'claude <agent-args> < /dev/null' |
tested: script, multi-turn, stream-json, --bg, message an interactive session and a -p receiver across accounts |
| R3 | WSL | other machine, Windows | <ssh> <wsl-alias> 'cd <win-dir> && <claude-exe> <agent-args> < /dev/null' |
reaches claude.exe; needs /login at that machine's console |
| R4 | Windows | this machine, WSL | wsl.exe -d <distro> --cd /tmp --exec <shell> -lc 'claude <agent-args> < /dev/null' |
tested: script from a native-Windows claude.exe (its Bash tool, Git Bash); list |
| R5 | Windows | other machine, WSL | ssh.exe <wsl-alias> 'claude <agent-args> < /dev/null' |
untested from a Windows origin (same hop as R2) |
| R6 | Windows | other machine, Windows | ssh.exe <wsl-alias> 'cd <win-dir> && <claude-exe> <agent-args> < /dev/null' |
untested from a Windows origin (same hop as R3) |
What ships with it
2 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.
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.
- 2d ago Changed · +11 lines 292c5a249ac4
- 7d ago Changed 3229d57416e5
- 13d ago Changed · +32 lines 7b93cd45bd5d
- 15d ago Changed · +6 lines aef1fc5302fb
- 22d ago Changed · -1 tokens per session cdc4c829efa0
- 25d ago Changed · -1 lines · -118 tokens per session ff0ae58425d3
- 26d ago Changed · +16 lines · +7 tokens per session 261e702a7621
- 28d ago Changed bd2b5a98ec5e
- 1mo ago Changed · +1 lines 1f2c9d2cc45e
- 1mo ago First seen · 170 lines · 226 tokens per session scan A a696ed6808d7
reach is a skill published in the GitHub repository melodic-software/claude-code-plugins (28 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 4,320 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-08.
Other skills, from other repositories
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
optimize-local-search
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.
test-with-examples
For example-driven development: test cases as specifications, input/output pairs, documentation through examples.
feature-optimiser
Deterministically audit and optimise a published feature page on the register ladder: struggling-moment heroes with zero implementation jargon, mechanism evidence relocated to section bodies and dropdowns in the HashiCorp / Stripe / Tailscale register. Runs an 11-section quality audit plus register-ladder checks (hero…