A set of instructions that routes an AI coding agent to selected skill collections instead of raw cached files. The description does not explain which skills or tasks it covers.

Use it for skill selection and routing when working with a curated collection of reusable agent instructions.

It is intended to avoid using unfiltered cache data, but the available information does not say what practical problem it solves in a project.

How abdulsamed1/AI-skills-bank configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to abdulsamed1/AI-skills-bank. 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/abdulsamed1/AI-skills-bank/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/abdulsamed1/AI-skills-bank

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/abdulsamed1/ai-skills-bank/agents-md/github.svg)](https://agentmods.dev/instructions/abdulsamed1/ai-skills-bank/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/abdulsamed1/ai-skills-bank/agents-md"><img src="https://agentmods.dev/badge/instructions/abdulsamed1/ai-skills-bank/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/abdulsamed1/ai-skills-bank/agents-md"><img src="https://agentmods.dev/badge/instructions/abdulsamed1/ai-skills-bank/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 858 This file is loaded in full into every session.

When invoked 858 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.

Model	Per session	Once invoked
Fable 5.1	$0.00858	$0.00858
Opus 5.5	$0.00343	$0.00343
Sonnet 5.5	$0.00172	$0.00172
Haiku 4.5	$0.00086	$0.00086

Measured 1mo ago against content hash 46a9db1cc1b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skills-bank 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 1mo 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 · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skills Bank — Agent Guardrail

DO NOT scan lib/ (2.1G, 10k SKILL.md, 122 repos). It is raw clone cache, not curated.

Canonical Discovery (3 hops, not 122)

Open skills-aggregated/AGENTS.md — pick hub from 4 (business, code-quality, frontend, server-side)
Open skills-aggregated/<hub>/SKILL.md — pick sub-hub (16 total, not 122)
Open skills-aggregated/<hub>/<sub-hub>/routing.csv — find skill_id by description, read src_path (points to lib/.../SKILL.md) or symlink <sub-hub>/<skill_id>/SKILL.md

Opencode Native (if synced)

When synced, hubs are also available via skill tool as 4 entries (business, code-quality, frontend, server-side) — 120 tokens, not 3840. Load hub via skill, then follow routing.csv.

Anti-Patterns

NEVER Glob **/SKILL.md on repo root (hits lib/ → 212k tokens)
NEVER read lib/SKILL.md (deleted router, was 122 repos)
ALWAYS use skills-aggregated/ routers + src_path source-of-truth

MCP Tools: code-review-graph

This project has a knowledge graph. Start with the code-review-graph MCP tools to narrow scope, then read the source. The graph is cheaper than scanning files and gives you structural context (callers, dependents, test coverage) that file search cannot.

When to use graph tools FIRST

Exploring code: semantic_search_nodes_tool or query_graph_tool instead of Grep
Understanding impact: get_impact_radius_tool instead of manually tracing imports
Code review: detect_changes_tool + get_review_context_tool instead of reading entire files
Finding relationships: query_graph_tool with callers_of/callees_of/imports_of/tests_for
Architecture questions: get_architecture_overview_tool + list_communities_tool

Verify in the source

Narrow scope with the graph, then read the source. Do not change code from graph output alone.
For any non-trivial change, read the implementation and the relevant tests before concluding.
Verify the exact source when touching behavior, database logic, migrations, retries, fallbacks, recovery, or compatibility code.
When the graph and the source disagree, the source wins. The graph may be stale or may not model that relationship.
An empty graph result can mean "not indexed" or "not statically visible", not "does not exist".

Read the full file on GitHub · 72 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.

1mo ago Changed · +46 lines · +538 tokens per session 46a9db1cc1b8
1mo ago Changed · -14 lines · -113 tokens per session scan B → A fe858ac99746
2mo ago Changed · -4 tokens per session 0269dd8a2410
2mo ago Changed · +14 lines · +112 tokens per session scan A → B a3a63780b312
2mo ago First seen · 26 lines · 325 tokens per session scan A e1b7ee61cbad

Subscribe to this mod's changes

skills-bank is an instructions file published in the GitHub repository abdulsamed1/AI-skills-bank (14 stars, last pushed 1mo ago), licensed MIT. It adds 858 tokens to every session, about $0.0034 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.

ai-skill ai-skill-file ai-skill-scanner ai-skills ai-skills-analysis ai-skills-manager

skills-bank next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skills-bankabdulsamed1/AI-skills-bank	Instructions file	14	1mo ago	MIT	A	858	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

AI-skills-bank: Instructions file for Codex