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.
npx agentmods add commands/agentis-tools/ctx/mapgit clone --depth 1 https://github.com/agentis-tools/ctxWhat 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 | $0.00000 | $0.00400 |
| Opus 5 | $0.00000 | $0.00200 |
| Sonnet 5 | $0.00000 | $0.00080 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
map 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 yesterday.
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.
What it actually says
ctx map
Generate a token-budgeted map of the codebase for LLM session bootstrap.
Synopsis
ctx map [OPTIONS]
Description
The map command condenses the index into a compact structural overview - modules, key symbols, and their relationships - that fits a fixed token budget. It is designed to be the first thing an AI assistant reads in a session: enough orientation to navigate the codebase without pasting whole files.
Prerequisites
ctx index
Options
| Option | Description | Default |
|---|---|---|
--budget <N> |
Maximum tokens in the map | 2000 |
--focus <PATH> |
Zoom the map on a path or module (more detail there, less elsewhere) | none |
--format <FMT> |
Output format: text, markdown, or json |
text |
Exit Codes
| Code | Meaning |
|---|---|
| 0 | Success (informational command) |
| 2 | Operational error (missing index) |
Examples
# Compact overview for a session start hook
ctx map --budget 2000
# Zoom on one subsystem
ctx map --focus src/parser --budget 4000
# Markdown for pasting into a PR description or issue
ctx map --format markdown
Caveats
- The map summarizes what the index knows: reindex after large changes, or the map lags the code.
- Tight budgets drop detail deterministically (least-connected symbols first); raise
--budgetif a module you need is missing.
See Also
- ctx smart - task-driven file selection (map is task-agnostic orientation)
- Quality Gates - using
ctx mapin a SessionStart hook
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.
- yesterday First seen · 58 lines · 0 tokens per session scan A 69c5198089e0
map is a command published in the GitHub repository agentis-tools/ctx (11 stars, last pushed 15d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 400 tokens. 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.
Other commands, from other repositories
coograph-review
Review the changes in scope for spec compliance, convention violations, logic bugs, and architectural issues. You review — you do not author. Never edit files.
coograph-verify
Verify that the described work is complete and correct. Provide evidence for every claim. You verify — you do not implement or fix style.
api-gen
Generate REST API endpoints with routes, validation, error handling, and tests.
component-gen
Generate React or Vue components with prop types, styling, accessibility, and tests.
code-review
Review staged git changes for bugs, security issues, and style violations.
pr-description
Generate a PR title and description from the current branch diff against main.