agents-market-installer

agents-market-installer is a skill for Claude Code, Codex from tt-a1i/agents-market. It costs 43 tokens per session (724 once invoked), scanned A, a copy of agents-market-installer, MIT.

A repository workflow for finding, previewing, and installing specialized coding helpers, called subagents, for Claude Code, Codex, or OpenCode.

In plain words
What is it for?
Use it to recommend a helper pack, inspect a registry, search for individual helpers, create a custom pack, preview changes, and install or check the result.
Why use it?
It reduces the work of choosing and setting up suitable coding helpers. It also shows the files, permissions, policy results, warnings, and source details before installation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Good fit Use it to recommend a helper pack, inspect a registry, search for individual helpers, create a custom pack, preview changes, and install or check the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tt-a1i/agents-market/codex-skill
Install

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.

Any agent
npx skills add tt-a1i/agents-market --skill codex-skill
Clone the repo
git clone --depth 1 https://github.com/tt-a1i/agents-market

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agents-market-installer

README.md
[![agentmods](https://agentmods.dev/badge/skills/tt-a1i/agents-market/codex-skill.svg)](https://agentmods.dev/skills/tt-a1i/agents-market/codex-skill)
Your own site
<a href="https://agentmods.dev/skills/tt-a1i/agents-market/codex-skill"><img src="https://agentmods.dev/badge/skills/tt-a1i/agents-market/codex-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 724 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 91% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00724
Opus 5 $0.00022 $0.00362
Sonnet 5 $0.00009 $0.00145
Haiku 4.5 $0.00004 $0.00072

Measured 7d ago against content hash 8e6de9f508a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agents-market-installer 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.

Origin

This is a copy

91% identical to agents-market-installer — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

integrations/codex-skill/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents Market Installer

Use the local agents-market CLI to recommend and install specialized coding subagent packs.

Workflow

  1. Inspect the repository briefly so you understand the project type.
  2. If the user provides a registry URL or bundle path, run agents-market registry info --registry <source> --json, summarize the source/version/checksum, then run agents-market registry lock --registry <source> after confirmation.
  3. Run agents-market apply --target all --json to preview the recommended pack, audit, policy result, and file diff.
  4. If the user names a pack, run agents-market apply <pack-id> --target all --json instead.
  5. If the user wants a small custom set, run agents-market search <query> --json, create a pack with agents-market pack create <pack-id> --agent <ids...> --out ./registry/packs, then preview it with agents-market apply <pack-id> --target all --json.
  6. Explain target files, permission implications, policy findings, warnings, and source/license status.
  7. After user confirmation, run agents-market apply <pack-id> --target all --yes.
  8. Verify install state with agents-market status --json, agents-market outdated --json, and agents-market doctor --strict --json.
  9. Summarize installed files, pack version state, health warnings, and how the user can invoke the new agents.

Target Selection

  • Use --target claude for Claude Code only.
  • Use --target codex for Codex only.
  • Use --target opencode for OpenCode only.
  • Use --target all when the user wants cross-tool support or does not know which tool they will use.

Safety

Prefer apply because it combines recommendation, audit, policy, diff, and guarded install. Use lower-level commands such as recommend, audit, policy check, diff, and install only when the user needs custom control or troubleshooting.

Use search --json for discovery. Do not use list --agents --json --full unless the user explicitly asks to inspect full prompt bodies; default list --agents --json is a compact index, and --full can be large on community registries.

Read the full file on GitHub · 44 lines

Changes

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.

  1. 7d ago First seen · 44 lines · 43 tokens per session scan A 8e6de9f508a3

Subscribe to this mod's changes

agents-market-installer is a skill published in the GitHub repository tt-a1i/agents-market (6 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 724 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to agents-market-installer, differing in 4 lines, and is treated as a copy.

Related

Other skills, from other repositories

agentplane

Use when a repository uses AgentPlane or the user wants a governed git-native workflow for planning, task execution, verification, and closure.

basilisk-labs/agentplane · 30 tokens

expo-eas-update

Publishing OTA updates with EAS Update, channels, runtime versions, branch management, and rollback strategy. Triggers on eas update, ota, over-the-air, runtime version, channel, branch, rollback, embedded update, asset selection, expo-updates, hot update, partial release, release cohort.

fatihkan/badi · 65 tokens

pentest-credentials

Credential testing methodology — hash crack selection, wordlist generation, password spray (advisory), default cred audit. Triggers on credential testing, hash crack, Hashcat, John the Ripper, password spray, wordlist generation, cupp, CeWL, Crunch, hashid, default password, credential stuffing.

fatihkan/badi · 69 tokens

pentest-ctf

CTF (Capture the Flag) challenge solving advisory — HackTheBox, TryHackMe, PicoCTF, web/pwn/rev/crypto/forensics. Triggers on CTF, HackTheBox, HTB, TryHackMe, THM, PicoCTF, OverTheWire, pwn, reverse engineering, crypto challenge, forensics challenge, stego.

fatihkan/badi · 84 tokens

pentest-exploit-chain

Multi-step exploit chain analysis — linking low/medium severity findings into a critical chain, stealth+impact scoring advisory. Triggers on exploit chain, attack chain, chain analysis, multi-step attack, kill chain, attack path, stealth scoring, impact analysis.

fatihkan/badi · 57 tokens

pentest-orchestrator

Authorized penetration testing engagement orchestrator — scope declaration, OPSEC tagging, evidence-handling discipline. Triggers on pentest, penetration test, red team, engagement, ROE, scope, security assessment, vulnerability assessment, ethical hacking. ADVISORY/DEFENSIVE: does not run live exploits; methodology…

fatihkan/badi · 75 tokens