find-context

find-context is a command for Claude Code from conorbronsdon/agent-context-os. It costs 33 tokens per session (596 once invoked), scanned A, original, MIT.

A command that finds Markdown context files related to a topic, using tags, filenames and headings.

In plain words
What is it for?
It helps load relevant files for topics such as authentication, rewrites or quarterly planning, then presents the matches ranked by how closely they fit.
Why use it?
It reduces the time spent searching through project notes when a task involves several areas of a codebase or documentation set.

Command for Claude Code

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.

agentmods
npx agentmods add commands/conorbronsdon/agent-context-os/find-context
Clone the repo
git clone --depth 1 https://github.com/conorbronsdon/agent-context-os

Made for: Claude Code.

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 find-context

README.md
[![agentmods](https://agentmods.dev/badge/commands/conorbronsdon/agent-context-os/find-context.svg)](https://agentmods.dev/commands/conorbronsdon/agent-context-os/find-context)
Your own site
<a href="https://agentmods.dev/commands/conorbronsdon/agent-context-os/find-context"><img src="https://agentmods.dev/badge/commands/conorbronsdon/agent-context-os/find-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 596 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.00596
Opus 5 $0.00016 $0.00298
Sonnet 5 $0.00007 $0.00119
Haiku 4.5 $0.00003 $0.00060

Measured 4d ago against content hash a514daad0b01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

find-context 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 4d 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.

.claude/commands/find-context.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/find-context — Find Relevant Files by Topic

Find and load the right context files for any topic, even when it spans multiple domains.

Instructions

1. Get the topic

The user will say /find-context <topic> (e.g., /find-context auth rewrite, /find-context q3 planning). This avoids colliding with Claude Code's built-in /context command.

2. Search (three strategies, in parallel)

Tag match — use Grep to search Markdown files for the topic in YAML tags: frontmatter (the strongest signal—the file was explicitly categorized).

Filename matchGlob for files with the topic keyword in their name.

Header matchGrep for # /## headings containing the topic across .md files. Skip sessions/ (unless the topic is from the last 3 days), node_modules/, and any vendored docs.

3. Rank and present

Combine, deduplicate, and rank by signal strength:

  1. Tag matches (highest — explicitly categorized)
  2. Filename matches
  3. Header matches (lowest — may be incidental)

Present a ranked list with the match type and line count:

CONTEXT FILES for "[topic]":

  [tag]  path/to/file.md — [first line or description] ([N] lines)
  [name] path/to/file.md — [first line or description] ([N] lines)
  [hdr]  path/to/file.md — [first line or description] ([N] lines)

Load all? (or specify which by number)

4. Load selected files

Read the selected files and give a one-line summary of what each contains relative to the topic. If more than 3 are selected, read only the first 30 lines of each and offer to load full content on request.

Tag Convention

Context files (not skills or commands) can carry a tags: line in YAML frontmatter so /find-context can find them by category rather than by incidental keyword:

---
tags: [auth, security, backend]
---

Tags are lowercase, short, and descriptive. Group them however fits your work — for example:

  • Domains: the areas you work in (backend, marketing, research)
  • Topics: recurring subjects (auth, pricing, onboarding)
  • Types: the kind of doc (strategy, reference, planning)

Read the full file on GitHub · 63 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.

  1. 4d ago First seen · 63 lines · 33 tokens per session scan A a514daad0b01

Subscribe to this mod's changes

find-context is a command published in the GitHub repository conorbronsdon/agent-context-os (21 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 596 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 2026-08-30.