What is only-skill-you-need?

A starter skill for beginners that sets up a project’s collection of agent skills and directs each task to the most suitable one.

Use it when installing skills for a new project or deciding which existing skill should handle a task. It can inspect the project, bootstrap a proposed skill set, and route requests.

It prevents overlapping or poorly matched skills from causing inconsistent instructions and helps establish project-wide defaults.

only-skill-you-need — Skill for Claude Code and Codex by Endokelp

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 Endokelp/Only-Skill-You-Need --skill only-skill-you-need

Clone the repo

git clone --depth 1 https://github.com/Endokelp/Only-Skill-You-Need

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/endokelp/only-skill-you-need/only-skill-you-need/github.svg)](https://agentmods.dev/skills/endokelp/only-skill-you-need/only-skill-you-need)

Your own site

<a href="https://agentmods.dev/skills/endokelp/only-skill-you-need/only-skill-you-need"><img src="https://agentmods.dev/badge/skills/endokelp/only-skill-you-need/only-skill-you-need/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/endokelp/only-skill-you-need/only-skill-you-need"><img src="https://agentmods.dev/badge/skills/endokelp/only-skill-you-need/only-skill-you-need.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 759 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 original No closer match found 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.

Model	Per session	Once invoked
Fable 5.1	$0.00152	$0.00759
Opus 5.5	$0.00061	$0.00304
Sonnet 5.5	$0.00030	$0.00152
Haiku 4.5	$0.00015	$0.00076

Measured 2mo ago against content hash 2842f85cddd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

only-skill-you-need 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 2mo ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/__init__.py, scripts/bootstrap.py, scripts/cli.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

only-skill-you-need

Announce: Using only-skill-you-need to [bootstrap | route this task].

This is the first skill. Do not skip it to "just start coding." Read the winners it names, then do the user's actual work.

Scripts live next to this file. Run them from the skill root (SKILL.md's directory).

python scripts/cli.py detect --root <project>
python scripts/cli.py status --root <project>
python scripts/cli.py bootstrap --root <project> --offline
python scripts/cli.py route --root <project> --offline "<user task>"
python scripts/cli.py --self-check

--offline uses the bundled seed list. Omit it to live-search via npx skills find. Never pass --apply until the user says yes.

Procedure

Run detect, then status.
If project_ledger_empty is true → bootstrap path. Print the proposed pack. Stop and ask before any install. After yes, run bootstrap with --apply, then npx skills add using the printed install_commands (or run those commands). Refresh STATUS.md.
Else run route "<user task>".
Read each winner's SKILL.md (installed copy under ~/.claude/skills, ~/.cursor/skills, or ~/.agents/skills) before doing the user's work.
Empty relevant slot → propose the live best from the route/bootstrap output. Wait. Install. Record via --apply or occupy through bootstrap.
Occupied slot + upgrade listed → mention the better skill. Do not replace it unless the user asks to switch.
Do the actual task following those skills.
Run status again so .agents/only-skill-you-need/STATUS.md is current.

Sticky rules

Empty slot → propose, install only after yes.
Occupied slot → keep the installed skill.
Same use-case → refuse a second install; it lands in rejected[].
Unknown source with under 100 installs → never propose.
Project ledger wins over global per slot.

Do not invent a parallel registry. Installs go through npx skills add <owner/repo> -s <skill> -g -y plus -a only for agents detect found.

Read the full file on GitHub · 60 lines

Files

What ships with it

14 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.

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.

2mo ago First seen · 60 lines · 152 tokens per session scan A 2842f85cddd1

Subscribe to this mod's changes

only-skill-you-need is a skill published in the GitHub repository Endokelp/Only-Skill-You-Need (28 stars, last pushed 2mo ago), licensed MIT. It adds 152 tokens to every session and 759 once invoked, about $0.0006 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 2026-08-30.

Building agents Claude Code agent-skills cursor

only-skill-you-need next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
only-skill-you-needEndokelp/Only-Skill-You-Need	Skill	28	2mo ago	MIT	A	152	Claude Code, Codex
x-tweet-by-conversationbrowser-act/skills	Skill	6.3k	8d ago	MIT	A	218	Claude Code, Codex
oma-scholarfirst-fluke/oh-my-agent	Skill	1.4k	today	MIT	A	30	Claude Code
pkf-writingPrismer-AI/PrismerCloud	Skill	1.4k	21d ago	MIT	A	78	Claude Code, Codex
monorepo-managementwshobson/agents	Skill	42k	3d ago	MIT	C	54	Claude Code
render-3d-product-showcasegooseworks-ai/goose-skills	Skill	1.3k	5d ago	MIT	A	159	Claude Code, Codex
render-airdrop-carouselgooseworks-ai/goose-skills	Skill	1.3k	5d ago	MIT	A	207	Claude Code, Codex

only-skill-you-need

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

only-skill-you-need

Procedure

Sticky rules

What ships with it

What this file has done since we first saw it

only-skill-you-need compared with skills from other repositories