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 anivaryam/anivaryam-plugins --skill proc-composegit clone --depth 1 https://github.com/anivaryam/anivaryam-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/anivaryam/anivaryam-plugins/proc-compose)<a href="https://agentmods.dev/skills/anivaryam/anivaryam-plugins/proc-compose"><img src="https://agentmods.dev/badge/skills/anivaryam/anivaryam-plugins/proc-compose.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 | $0.00149 | $0.04143 |
| Opus 5 | $0.00075 | $0.02072 |
| Sonnet 5 | $0.00030 | $0.00829 |
| Haiku 4.5 | $0.00015 | $0.00414 |
Grade A, and why
proc-compose 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 7d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
proc-compose
Local process orchestrator. One YAML, one lifecycle, one log stream. Not Docker — no containers, no images, just sh -c with supervision.
Repo: github.com/anivaryam/proc-compose. Binary: proc-compose (installed via brokit install proc-compose, ~/.local/bin/, or go install).
brokit install also lays down companions: merge-port, tunnel, env-vault, proxy-relay. Easiest way to unlock the merge: block and public tunnels.
When to reach for it
Use proc-compose when the project needs >1 long-running command and the user wants them tied together. Signals:
proc-compose.ymlorproc-compose.yamlpresent (walks parent dirs from cwd)- frontend + backend dev pair, microservices, worker+queue, prestart migrations
- container entrypoint that runs multiple children
- "give me a public URL" via the
tunnelcompanion
Do NOT use for: single-process projects, Docker stacks (use docker compose), production multi-host orchestration (use k8s/nomad).
Workflow
New project (no config yet)
proc-compose bootstrap # dry run, prints proposed yaml
proc-compose bootstrap --verify # parse-check generated config
proc-compose bootstrap --write # create proc-compose.yml
proc-compose bootstrap --json # machine-readable scan output
bootstrap builds on doctor. Scans Node/Go/Python layouts, detects npm/yarn/pnpm/bun runners, Vite/Next/SvelteKit/Astro, Go cmd/**/main.go, Django/Flask/Uvicorn/Hypercorn. Refuses to overwrite without --force. Always read the dry-run output before --write — cheapest review.
proc-compose init --template node|go|python|minimal for a hand-edit starting point instead of detection.
Existing project
proc-compose validate # parse-only, catches unknown fields / bad restart / cycles
proc-compose list # show defined processes (alias: l)
proc-compose up # foreground, Ctrl+C stops all
proc-compose up frontend backend # subset (deps auto-included)
proc-compose up --dry-run # resolve + list, no start
proc-compose up --silent --log-file app.log # daemonize
proc-compose monitor # TUI on running daemon (alias: m)
proc-compose status # one-shot snapshot
proc-compose status --json # scriptable
proc-compose logs -n 200 # tail default log (-n 0 = full file)
proc-compose restart backend # one process
proc-compose reload # re-read config, restart changed defs
proc-compose stop # SIGTERM, 10s grace, then SIGKILL
proc-compose stop --timeout 30 # extend graceful window
proc-compose stop --force # SIGKILL now
proc-compose uninstall --name myapp # remove systemd unit from --survive
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.
- 7d ago First seen · 347 lines · 0 tokens per session scan A ae23a0df88c7
proc-compose is a skill published in the GitHub repository anivaryam/anivaryam-plugins (2 stars, last pushed 3mo ago), licensed MIT. It adds 149 tokens to every session and 4,143 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…