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 reidemeister94/development-skills --skill phone-a-friendgit clone --depth 1 https://github.com/reidemeister94/development-skillsWrote 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/reidemeister94/development-skills/phone-a-friend)<a href="https://agentmods.dev/skills/reidemeister94/development-skills/phone-a-friend"><img src="https://agentmods.dev/badge/skills/reidemeister94/development-skills/phone-a-friend/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/reidemeister94/development-skills/phone-a-friend"><img src="https://agentmods.dev/badge/skills/reidemeister94/development-skills/phone-a-friend.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 | $0.00027 | $0.00757 |
| Opus 5.5 | $0.00011 | $0.00303 |
| Sonnet 5.5 | $0.00005 | $0.00151 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
phone-a-friend 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 27d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phone a friend
Get a second opinion from the other model family before sharing the first reviewer's conclusions. Use one rebuttal round to resolve findings with evidence. Escalate unresolved material disagreements; never run a third round.
Scope and partner
Plan mode reviews the given plan path, or the active task plan. Review mode reviews the requested scope, or current branch changes. Ask when the mode is ambiguous.
If PHONE_A_FRIEND=1 is set, refuse because this session is already the partner.
Detect the host and call the other CLI without interactive permission prompts:
- From Claude Code:
PHONE_A_FRIEND=1 codex exec -c model_reasoning_effort="xhigh" --sandbox read-only --cd <repo> --json --output-last-message <file> "<packet>". Resume with the same environment, reasoning, sandbox, and repository flags beforeresume <session-id> "<rebuttal>". - From Codex:
PHONE_A_FRIEND=1 claude -p --permission-mode plan --effort xhigh --output-format json "<packet>". Resume with the same environment, permission mode, effort, and--resume <session-id>flags.
Use the configured high-capability model and highest supported reasoning effort. The partner must run unattended and read-only. Never use Claude's bypass permission mode. If the partner CLI is missing or fails, report it and stop. A same-family review is not a second opinion.
Neutral packet
Send the user's requirements verbatim, the plan or diff, referenced paths, and applicable project rules. Do not include the host's conclusions or suspected defects. Keep packets, verdicts, and event logs in a temporary directory outside the reviewed repository.
Tell the partner:
- Report material findings only. Zero findings is valid.
- Each finding needs a location, falsifiable claim, evidence, impact, falsifier, likelihood, and confidence.
- Missing context must be named, not guessed.
- Stay read-only. Do not commit, merge, push, write files, modify databases, or call mutating production endpoints.
- In plan mode, give a rewrite mandate for a contested section instead of an accept or reject label.
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.
- 27d ago First seen · 70 lines · 27 tokens per session scan A ea309cc6da84
phone-a-friend is a skill published in the GitHub repository reidemeister94/development-skills (12 stars, last pushed 27d ago), licensed MIT. It adds 27 tokens to every session and 757 once invoked, about $0.0001 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 2026-09-20.
Other skills, from other repositories
mutation-test
Mutation testing with two engines. Uses the project's NATIVE mutation runner (StrykerJS / Infection / mutmut / PIT / cargo-mutants) when one is configured — installing it on explicit consent when it is not — for a reproducible, comparable score; and an LLM-guided engine for the mutation classes native mutators cannot…
review
Structured code review with parallel audit agents, confidence-scored triage, and optional auto-fix. Examines uncommitted changes, staged diffs, commit ranges, or specific paths. Produces a tiered report (MUST-FIX / RECOMMENDED / NIT) backed by evidence, then optionally applies fixes with verification.
write-tests
Write tests for existing production code. Processes ONE file at a time through a full pipeline: analyze, inventory (frozen BEFORE writing), write, executable coverage gate, verify, blind coverage audit, adversarial review, log. Uses CodeSift for discovery and analysis when available. Modes: [path] (specific target)…
db-audit
Database performance and safety audit. 70+ checks across 13 dimensions (DB1-DB13): query patterns, indexes, schema design, connections, transactions, migrations, caching, query optimization, ORM anti-patterns, observability, data lifecycle, DB security, and migration deployment safety. Code-level checks for all ORMs.…
brainstorm
Explores a codebase, researches the problem space, and produces an approved design specification before any code is written. Use when the user wants to create a new feature, add significant functionality, redesign a subsystem, or build something that touches multiple parts of the project.
code-audit
Batch audit of production files against CQ1-CQ40 quality gates and CAP1-CAP29 anti-patterns. Tiered output (A/B/C/D), critical gate enforcement, evidence-backed scoring, cross-file pattern analysis, and prioritized execution plan. Flags: zuvo:code-audit all | [path] | [file] | --deep | --quick | --services |…