ctx CLAUDE.md

Operating instructions for ctx, a code-intelligence and project-tracking tool used in the agentis-tools repository.

In plain words
What is it for?
Use them when developing ctx to query symbols and code relationships, run checks and scoring, follow version and workflow policies, and track work in Linear.
Why use it?
They give contributors a consistent way to inspect source code, check changes, follow repository governance, and avoid editing generated files or bypassing review rules.

Instructions file

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/agentis-tools/ctx/claude-md
Clone the repo
git clone --depth 1 https://github.com/agentis-tools/ctx
Per session 315 This file is loaded in full into every session.
When invoked 315 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.00315 $0.00315
Opus 5 $0.00158 $0.00158
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00032 $0.00032

Measured 2d ago against content hash 48ff17134bdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

ctx CLAUDE.md scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- governance-instructions:v1 -->
CLAUDE.md · 31 lines

What it actually says

Claude operating instructions for ctx

Follow AGENTS.md as the root contributor contract. Read governance/agent-workflow.md before editing and governance/versioning.md before touching any compatibility or release surface. docs/ is public product documentation; internal instructions and maintainer policy belong only under governance/.

ctx-assisted development

Prefer the repository index for code intelligence, then verify against source:

  • ctx map --budget 2000
  • ctx query find <name> / ctx search <query>
  • ctx source <symbol> / ctx explain <symbol>
  • ctx similar <symbol> before adding an implementation
  • ctx check and ctx score --against <base> before handoff

Do not edit generated .claude/hooks/ctx/, .codex/ harness files, plugin manifests, release notes, lockfile versions, or CLI contract snapshots by hand. Use their repository scripts. Never bypass a compatibility/version/security gate or describe a human-review rule as automatically enforced.

Project tracking

Work is tracked in Linear under team agentis (AGE), project ctx: https://linear.app/itkonsult/project/ctx-7625ddcc6dcb. New repository issues belong to that team/project when issue creation is explicitly requested.

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 · 31 lines · 315 tokens per session scan C 48ff17134bdd

Subscribe to this mod's changes

ctx CLAUDE.md is an instructions file published in the GitHub repository agentis-tools/ctx (11 stars, last pushed 15d ago), licensed Apache-2.0. It adds 315 tokens to every session, about $0.0016 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.