wikiskill

wikiskill is a skill for Codex from Stahl-G/briefloop. It costs 62 tokens per session (2,012 once invoked), scanned A, original, MIT.

A workflow for improving reusable coding-agent skills through example tasks, scores, feedback, and a saved knowledge base. It can start, resume, check, or export an improvement run.

In plain words
What is it for?
Use it to evaluate a skill on examples, record feedback, continue an existing improvement run, inspect its status, or export the retained version.
Why use it?
It keeps feedback and past results together so a recurring agent task can be improved without starting duplicate work.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Good fit Use it to evaluate a skill on examples, record feedback, continue an existing improvement run, inspect its status, or export the retained version.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stahl-g/briefloop/entry-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 Stahl-G/briefloop --skill entry-skill
Clone the repo
git clone --depth 1 https://github.com/Stahl-G/briefloop

Made for: 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 wikiskill

README.md
[![agentmods](https://agentmods.dev/badge/skills/stahl-g/briefloop/entry-skill/github.svg)](https://agentmods.dev/skills/stahl-g/briefloop/entry-skill)
Your own site
<a href="https://agentmods.dev/skills/stahl-g/briefloop/entry-skill"><img src="https://agentmods.dev/badge/skills/stahl-g/briefloop/entry-skill/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.

agentmods 80×15 button for wikiskill

Your own site · 80×15
<a href="https://agentmods.dev/skills/stahl-g/briefloop/entry-skill"><img src="https://agentmods.dev/badge/skills/stahl-g/briefloop/entry-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,012 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.02012
Opus 5 $0.00031 $0.01006
Sonnet 5 $0.00012 $0.00402
Haiku 4.5 $0.00006 $0.00201

Measured today against content hash 9e18ac596b96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

wikiskill 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 today.

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.

src/wikiskill/resources/product/entry-skill/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WikiSkill

Help the user improve a recurring agent task through experience. Use the user's current agent, chosen model and normal tools. WikiSkill owns the work requests, records, scores and retained skill versions; it does not select a model or change host permissions.

Start with the user's intent

  • Remember feedback: save it with wikiskill feedback; do not start an improvement run merely because a note was added.
  • Improve a skill: identify the task examples, evaluation criterion, current skill if any, and the user's intended effort/budget. Reuse information already provided. Begin with one round unless the user requests more; there is no hard sample or round cap.
  • Resume: read wikiskill status, then use wikiskill next in the existing workspace. Do not initialize a duplicate run.
  • Check only: use wikiskill status and existing artifacts; do not start more work.
  • Use the result: export the retained skill. Install or replace an existing skill when the user has authorized that destination.

Read workflow commands and formats when preparing tasks or operating the loop. Use wikiskill capabilities to discover the installed interfaces. If the package is missing, use the user's selected checkout or the official repository. Prefer an existing project virtual environment; otherwise create a project-local venv and use its Python and wikiskill executables. Do not default to modifying the system/global Python environment. Installation executes package build code, so inspect unfamiliar sources first. The product path works without a Codex CLI account.

If another skill-improvement tool such as skill-evolve is installed, compare its description rather than assume the tools are equivalent. Keep ordinary creation/rewriting with the user's chosen editor. Choose WikiSkill for the task-score-Wiki-validation cycle, or when the user names WikiSkill. Do not run two improvement controllers for the same task or recommend uninstalling the other skill merely because both are present.

Read the full file on GitHub · 75 lines

Files

What ships with it

3 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.

  1. today First seen · 75 lines · 62 tokens per session scan A 9e18ac596b96

Subscribe to this mod's changes

wikiskill is a skill published in the GitHub repository Stahl-G/briefloop (9 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 2,012 once invoked, about $0.0003 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 2026-09-12.

Related

Other skills, from other repositories

class.organize

Organize class materials, meetings, and student follow-up.

XiaoLuoLYG/GOD · 16 tokens

openprd-learning-review

A guide for turning completed OpenPrd work into a structured learning package. It can organize evidence, explanations, examples, reference material, and an HTML reader for long-term study.

mileson/openprd · 48 tokens

creative-commons-explainer

Explains a specific Creative Commons licence in plain language, telling a media professional exactly what they can and cannot do with the licensed content — including attribution requirements, commercial use rules, and derivative work restrictions.

ur-grue/autopunk-media-skills · 47 tokens

fact-sheet-writer

Produces a concise, structured fact sheet on any topic for production teams — covering key facts, essential terminology, background context, and common misconceptions — so crew and contributors arrive on set informed.

ur-grue/autopunk-media-skills · 42 tokens

presenter-briefing-writer

Drafts a concise, production-ready briefing document that gives a presenter or on-screen moderator everything they need to walk into a shoot or live recording fully prepared.

ur-grue/autopunk-media-skills · 39 tokens

topic-glossary-writer

Produces a plain-language glossary of essential terms for a complex or specialist topic, written so that a journalist, presenter, or producer with no prior expertise can understand and use the terms correctly before entering an interview or writing a script.

ur-grue/autopunk-media-skills · 52 tokens