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 agentmods add skills/bnet47/codexicon/discovernpx skills add bnet47/codexicon --skill discovergit clone --depth 1 https://github.com/bnet47/codexiconWhat 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 | $0.00030 | $0.00496 |
| Opus 5 | $0.00015 | $0.00248 |
| Sonnet 5 | $0.00006 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
discover 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 2d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discover
Announce: "I'm using discover to define the project before we choose how to build it."
1. Check the gate
Inspect agent_docs/briefs/ and the identity section in AGENTS.md.
- If an approved project charter already exists, summarize it and ask whether the user wants to revise it. Do not create a duplicate.
- If this is an established repository with clear project identity, stop and route the request to the relevant feature workflow.
2. Build understanding
Ask one question at a time and stop as soon as the answer is clear. Keep the exchange focused on unresolved decisions.
Cover only unresolved parts of:
- What is painful, missing, or expensive today?
- Who experiences it, and what do they do now?
- What concrete change should the project create for that person?
- Why is this worth solving now?
- What constraints and existing systems are real?
- What is explicitly not part of the project?
Do not choose a language, framework, database, or deployment target in this workflow.
3. Reflect before writing
Return a two- or three-sentence synthesis of the problem, person, and intended outcome. Resolve material corrections before saving.
4. Write the charter
Save agent_docs/briefs/charter-[project-slug].md:
# Project Charter: [Project name]
**Date:** [YYYY-MM-DD]
**Status:** Approved
## Problem
[Pain, affected person, and current cost.]
## Intended user
[A specific person or role and their context.]
## Outcome
[The observable change when the project succeeds.]
## Why now
[Why the work matters now.]
## Constraints
- [Real limit or dependency.]
## Non-goals
- [Explicit boundary.]
## Success signals
- [Observable evidence without prescribing a feature.]
## Open questions
- [Unresolved item, or "None".]
Self-check that the charter describes a problem and outcome rather than a predetermined solution, and that non-goals are meaningful.
5. Hand off
Offer $init to configure the technical environment. Do not commit, push, or open a PR unless the user separately asks.
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.
- 2d ago First seen · 76 lines · 30 tokens per session scan A 0239f27b1b8d
discover is a skill published in the GitHub repository bnet47/codexicon (5 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 496 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
当用户需要对PDF文件进行任何操作时，请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF，请使用此技能。.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.