Borrowing it
Nothing to install: this file belongs to friedbotstudio/baseline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/friedbotstudio/baseline/main/.claude/skills/companion/SKILL.mdgit clone --depth 1 https://github.com/friedbotstudio/baselineWrote 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/friedbotstudio/baseline/companion)<a href="https://agentmods.dev/skills/friedbotstudio/baseline/companion"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/companion/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/friedbotstudio/baseline/companion"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/companion.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 | $0.00130 | $0.02004 |
| Opus 5.5 | $0.00052 | $0.00802 |
| Sonnet 5.5 | $0.00026 | $0.00401 |
| Haiku 4.5 | $0.00013 | $0.00200 |
Grade B, and why
companion 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 1mo 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.
`off` and `status` find the active peer through this marker. `.claude/state/` is gitignored. How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
companion — be a session peer on an org-team channel
Experimental. This skill is part of org mode (Article X — multi-session coordinated workflows), which is opt-in and off by default (velocity.org_mode.enabled). The single-session workflow is unaffected by anything here.
It turns the current Claude Code session into a session peer on a coordination channel, so a feature can be worked by a small pod of real sessions instead of by one. Instead of pasting register_peer / claim_task / signal_done calls by hand, you type /companion on <channel_id>.
The bounded-peer contract (Article X — non-negotiable)
A peer decides in its own lane and escalates out of it. When acting as a companion you SHALL:
- Stay a peer. You are a peer on this channel for the whole session, even if the same human also runs the lead session elsewhere. You SHALL NOT arbitrate yields, release or re-dispatch lanes, answer other peers, or decline a claimable lane on the belief that you are the lead. If a lane is claimable and yours to take (no assignee, or assigned to you), take it.
- Know who you are. You are the exact
peer_idyou registered as, and no other. Never infer identity from a task push — atask-availablefor a lane assigned to another peer is not yours, and a rejected claim does not mean you should change who you are. - Decide in-lane. How to structure a function, which existing helper to reuse, where a boundary sits — those are yours to make, in your own main context. That is what makes a peer a peer rather than a worker.
- Escalate out-of-lane. A cross-lane choice (its answer changes another lane) or an un-decidable one (it needs design or product judgment) is not yours. Task-bound →
yield_fork(...)and stop that lane. Free-form →ask_lead(...)and continue if you can. The lead answers viaanswer_peer; read it back withsprint_status. - Never send a free-form directive over the channel. The message types are a closed set; coordination travels over it, judgment does not.
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.
- 1mo ago First seen · 86 lines · 130 tokens per session scan B 9ddce4d22a75
companion is a skill published in the GitHub repository friedbotstudio/baseline (14 stars, last pushed 13d ago), licensed Apache-2.0. It adds 130 tokens to every session and 2,004 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
i18n-check
An internationalization (i18n) check for software that supports multiple languages. It compares translation files with the text and translation keys used by the code.
vue-best-practices
A review checklist for Vue 2 and Vue 3 components, covering component names, prop declarations, TypeScript casts, API styles and complex template expressions.
gdpr-audit
GDPR compliance audit of code, plans, schemas, or IaC. Produces a findings report with article citations, severity, confidence, and fixes; flags evidence gaps. Not a substitute for a DPO/lawyer.
cognitive-walkthrough
Deep-dive usability evaluation of specific user tasks. Simulates novice user cognition step-by-step to identify learnability issues, unclear actions, and points of confusion.
owasp-ai-testing
AI trustworthiness testing using OWASP AI Testing Guide v1. Execute 32 test cases across 4 layers (Application, Model, Infrastructure, Data) with practical payloads and remediation.