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/harnessgit 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 | $0.02167 |
| Opus 5 | $0.00000 | $0.01084 |
| Sonnet 5 | $0.00000 | $0.00433 |
| Haiku 4.5 | $0.00000 | $0.00217 |
Grade A, and why
harness 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ctx harness
Package ctx as an AI coding harness integration (Claude Code).
Synopsis
ctx harness init [--target claude|codex] [--mode local|plugin] [--force] [--json]
ctx harness compat --require <SEMVER>
ctx harness doctor [--json]
Description
The harness command wires the ctx quality suite into an AI coding harness. Supported targets are Claude Code (--target claude, the default) and Codex (--target codex); unknown targets are rejected with exit code 2 and a list of supported values.
Codex
ctx harness init --target codex writes trusted-project lifecycle configuration to
.codex/hooks.json, scripts under .codex/hooks/ctx/, and the shared starter
.ctx/rules.toml. It prints a guidance block for manual inclusion in AGENTS.md.
Review and trust new or changed hook definitions with /hooks before relying on them.
ctx harness init --target codex --mode plugin creates a distributable Codex plugin
with .codex-plugin/plugin.json, lifecycle hooks, the ctx skill, an optional MCP
configuration, and .agents/plugins/marketplace.json for local installation.
Everything init writes comes from templates embedded in the ctx binary, and every generated file carries a header:
# generated by ctx v0.2.1 — regenerate with 'ctx harness init'
# ctx:checksum sha256:<hex>
The checksum makes regeneration safe: on re-run, files that still match their recorded checksum are regenerated in place, while files you have modified (or files ctx never generated) are skipped with a warning. --force overwrites them. JSON files cannot carry comments, so they are tracked in a manifest, .ctx/harness.lock, instead.
Two files get special treatment:
.ctx/rules.tomlis never overwritten once it exists, not even with--force— it encodes your policy, not ctx's..claude/settings.jsonis never edited by ctx at all;initprints a snippet for you to merge manually.
init --mode local (default)
Wires the current project's .claude/ directory:
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.
- 2d ago First seen · 174 lines · 0 tokens per session scan A f141b98d7bdb
harness 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 2,167 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
approve-swarm
Record human approval of a swarm plan. swarm-dispatch will not run until this approval token exists. Must be user-invoked — Claude cannot approve.
harness-parallel
Run the parallel Auto-Harness orchestration flow with worktree workers. /auto-harness:harness-parallel.
harness
Run the full Auto-Harness orchestration flow. /auto-harness:harness.
mcp-manager
Manage MCP servers across Claude Code, Cursor, Codex, and OpenCode.
evolve
Analyze instincts and suggest or generate evolved structures.
harness-gate
Gate the agent setup on corpus-validated rules (gating tier). Fast, no LLM, exits nonzero on any finding. Suitable for CI and pre-commit.