ctx AGENTS.md

Repository instructions for CTX Fit, a tool that tests coding setups on a repository and selects the least expensive reliable option. They explain its commands, decision rule, source layout, and verification process.

In plain words
What is it for?
Useful for changing repository profiling, candidate evaluation, configuration selection, command-line behavior, applying changes, or generating pull-request details.
Why use it?
They prevent changes from confusing cost, reliability, and simplicity, and distinguish read-only checks from actions that can spend money or write files.

Instructions file for CodexOpenCode

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 instructions/stevesolun/ctx/agents-md
Clone the repo
git clone --depth 1 https://github.com/stevesolun/ctx

Made for: Codex, OpenCode.

Per session 1,695 This file is loaded in full into every session.
When invoked 1,695 The same file — it is already loaded in full.
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 $0.01695 $0.01695
Opus 5 $0.00847 $0.00847
Sonnet 5 $0.00339 $0.00339
Haiku 4.5 $0.00169 $0.00169

Measured 2d ago against content hash 299b903b2972, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ctx 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 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.

AGENTS.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ctx repository notes

The product

CTX Fit finds the cheapest AI coding setup that reliably works on a given repository, and produces the winning configuration as a reviewable change.

The winner is chosen by a lexicographic rule, not a score: filter candidates on a reliability floor, then minimize attributable cost, then tie-break toward simplicity. "Keep your current setup" is a valid and expected answer.

ctx is the human command and ctx fit is the product; older harness commands live under ctx advanced. ctx-mcp-server is the machine contract name. A few maintenance console scripts (ctx-init, ctx-scan-repo, ctx-source-registry, ctx-telemetry-*) still ship — ADR-001's collapse to two entry points is the destination, not yet the state.

ctx fit                      # free, local, read-only: profile + readiness
ctx fit --dry-run            # what a full evaluation would involve
ctx fit --test --budget 10   # evaluate candidates; spending requires both flags
ctx fit --apply              # write the winning configuration
ctx fit --pr                 # print a PR body and branch name; commits nothing

Where the code lives

  • src/ctx/cli/fit.py — the ctx fit subcommand: argument surface, human and --json rendering, apply/PR handling. Registered from src/ctx/cli/run.py, which is the ctx console-script entry point (ctx = "ctx.cli.run:main").
  • src/ctx/fit/ — the engine, one concern per module: profile.py (normalized repository profile), verification.py (discovering the repository's own test/typecheck/lint/build commands), readiness.py, tasks.py (representative tasks derived from repository history), candidates.py and release_catalog.py (bounded candidate generation), experiment.py (resolve, plan, run), execution.py (trial execution with adaptive reliability stopping), live_runner.py and providers.py (driving a real coding agent), recommend.py (choosing a winner, or refusing to), apply.py (recommendation → reviewable repository changes and a PR body).
  • src/tests/fit/ — the Fit test suite.

Read the full file on GitHub · 138 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. 2d ago First seen · 138 lines · 1,695 tokens per session scan A 299b903b2972

Subscribe to this mod's changes

ctx AGENTS.md is an instructions file published in the GitHub repository stevesolun/ctx (581 stars, last pushed 9d ago), licensed MIT. It adds 1,695 tokens to every session, about $0.0085 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.