agentmods.dev

skills: Instructions file for Codex

AGENTS.md

skills AGENTS.md is an instructions file for Codex, OpenCode from prathamdby/skills. It costs 412 tokens per session, scanned A, original, MIT.

Repository instructions for creating agent skills, which are reusable rules that guide an coding agent's work. They define the required writing, documentation, and self-check process.

In plain words
What is it for?
Use them when adding or updating skills in the prathamdby/skills repository, including planning the change, updating documentation, and checking files before committing.
Why use it?
They make skill additions follow the same reviewable process each time and prevent missing user approval, README updates, or final checks.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is prathamdby/skills's own configuration. It tells Codex and OpenCode how to work on skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skills configures →

not rated 6repo changed 29d ago A scan 412 tokens original MIT
View source ↗ prathamdby/skills
Reuse

Borrowing it

Nothing to install: this file belongs to prathamdby/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/prathamdby/skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/prathamdby/skills

Made for: Codex, OpenCode.

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 skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/prathamdby/skills/agents-md/github.svg)](https://agentmods.dev/instructions/prathamdby/skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/prathamdby/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/prathamdby/skills/agents-md/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 skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/prathamdby/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/prathamdby/skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 412 This file is loaded in full into every session.
When invoked 412 The same file — it is already loaded in full.
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 $0.00412 $0.00412
Opus 5.5 $0.00165 $0.00165
Sonnet 5.5 $0.00082 $0.00082
Haiku 4.5 $0.00041 $0.00041

Measured 29d ago against content hash 39a999e8d667, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skills AGENTS.md 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 29d 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.

AGENTS.md · 36 lines

What it actually says

Skill authoring

Skills make the agent follow a predictable process, not produce identical output.

Authority and ownership

  • Before writing a skill, propose its name, location, options, and structure; obtain explicit user confirmation. Approval to implement that plan counts.
  • Skills live at skills/<category>/<name>/SKILL.md, normally in engineering/ or personal/. Use this tree, not .agents/skills/.
  • The leaf owns invocation, options, procedure, and terminals; routers own order.
  • Keep every-run instructions inline. Disclose branch-only material through a pointer naming both the condition and the required action. No read-first gate.
  • Preserve behavior when pruning. Remove a guardrail only with behavioral evidence.

Before committing

Run bash scripts/skill-guards.test.sh, then check every touched skill:

  1. Frontmatter name matches its directory, is kebab-case, and is at most 64 characters.
  2. description exists and is at most 1024 characters.
  3. SKILL.md is at most 100 lines.
  4. README has its /<name> Quickstart entry and Reference link.
  5. Real .md links and backticked paths resolve; ignore <placeholder> paths.
  6. Claude plugins[0].skills exactly matches the sorted skill-directory set.
  7. Every non-router leaf has exactly one primary action playbook; all playbook leaves and participants resolve. Here the router exception is prath-mode.

When adding, renaming, or removing a skill, apply the README and playbook maintenance procedure in authoring/README.md. When drafting or restructuring agent-facing documents, apply its pointer, option, and ownership rules. For behavior changes or compression, run the relevant cases in authoring/verification.md.

README describes whole-skill intent. Reread the full leaf before changing its entries; procedural refinements alone do not require README changes.

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. 29d ago Changed · -127 lines · -1,449 tokens per session 39a999e8d667
  2. 1mo ago Changed · +14 lines · +154 tokens per session 7205d600b22f
  3. 1mo ago Changed · +19 lines · +264 tokens per session d2af42e9e19d
  4. 1mo ago Changed · -1 lines · +56 tokens per session 94b3f6871168
  5. 1mo ago Changed · +2 lines · +31 tokens per session f6283286afe1
  6. 2mo ago First seen · 129 lines · 1,356 tokens per session scan A a8d750e15e9f

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository prathamdby/skills (6 stars, last pushed 5d ago), licensed MIT. It adds 412 tokens to every session, about $0.0016 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 2026-08-31.

Building agents
Related

skills AGENTS.md compared with instructions from other repositories

skills AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skills AGENTS.mdprathamdby/skillsInstructions file65d agoMITA412Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode