clare: Command for Claude Code

.claude/commands/clare2-corpus-capture.md

clare2-corpus-capture is a command for Claude Code from jketreno/clare. It costs 18 tokens per session (989 once invoked), scanned A, original, MIT.

A capture setup that records normalized interactions from supported coding agents in a shared local CLARE₂ corpus. The corpus is a collection of recorded sessions organized by project for later processing.

In plain words
What is it for?
Use it to configure capture for Claude Code, Codex, GitHub Copilot, or Roo/Zoo Code, and to connect each project's corpus directory to the shared local storage.
Why use it?
It gives different agents a consistent event format and keeps their project sessions available to the local CLARE₂ pipeline.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is jketreno/clare's own configuration. It tells Claude Code how to work on clare itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything clare configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/clare-installer.sh --update --target /path/to/project.

Reuse

Borrowing it

Nothing to install: this file belongs to jketreno/clare. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jketreno/clare/main/.claude/commands/clare2-corpus-capture.md
Clone the repo
git clone --depth 1 https://github.com/jketreno/clare

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 clare2-corpus-capture

README.md
[![agentmods](https://agentmods.dev/badge/commands/jketreno/clare/clare2-corpus-capture/github.svg)](https://agentmods.dev/commands/jketreno/clare/clare2-corpus-capture)
Your own site
<a href="https://agentmods.dev/commands/jketreno/clare/clare2-corpus-capture"><img src="https://agentmods.dev/badge/commands/jketreno/clare/clare2-corpus-capture/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for clare2-corpus-capture

Your own site · 80×15
<a href="https://agentmods.dev/commands/jketreno/clare/clare2-corpus-capture"><img src="https://agentmods.dev/badge/commands/jketreno/clare/clare2-corpus-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 989 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00018 $0.00989
Opus 5 $0.00009 $0.00495
Sonnet 5 $0.00004 $0.00198
Haiku 4.5 $0.00002 $0.00099

Measured 10d ago against content hash 08717f85b8bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

clare2-corpus-capture 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 10d 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/clare2-corpus-capture.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLARE2 Corpus Capture

Use deterministic lifecycle hooks to send useful agent interactions into the local CLARE2 corpus. Sessions are captured per-project under a shared user corpus at ~/.config/clare/corpus, partitioned by project name. Each project builds its own adapter.

Agent support matrix

Agent Capture supported Notes
Claude Code Yes Visible message deltas, elicitation, tools, subagents, compaction, and session lifecycle in .claude/settings.json
Codex 0.144.1 Yes Final responses, elicitation, tools, subagents, and compaction in .codex/hooks.json
GitHub Copilot Yes Elicitation, tools, subagents, compaction, failures, and lifecycle in .github/hooks/clare2-corpus.json; assistant text fallback is opt-in
Roo/Zoo Code Prompt-level .roo/rules/clare.md emits equivalent normalized events; upstream has no deterministic repository hook API

Configuration

clare-installer.sh sets CLARE2_CORPUS_ROOT automatically, creates ~/.config/clare/corpus, and symlinks the project's corpus/ directory there so the pipeline container resolves the same data. Run:

./scripts/clare-installer.sh --update --target /path/to/project

If you need to set it manually:

export CLARE2_CORPUS_ROOT="$HOME/.config/clare/corpus"

CLARE2_SESSION_FILE takes precedence when an existing wrapper or command has already initialized a session. CLARE2_PROJECT_ID overrides the project name derived from git rev-parse --show-toplevel basename (used by default).

Text content is redacted and limited to 12,000 characters by default. Set CLARE2_CAPTURE_MAX_CHARS to a smaller non-negative integer, or 0 to disable prompt, response, and correction text capture while retaining lifecycle and tool outcome events.

Copilot's documented agentStop hook does not expose assistant text. By default CLARE records a privacy-safe turn_complete event. To explicitly opt in to parsing Copilot's unstable private transcript format for assistant text, set CLARE2_COPILOT_TRANSCRIPT_FALLBACK=1 before starting Copilot.

Read the full file on GitHub · 118 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. 10d ago First seen · 118 lines · 18 tokens per session scan A 08717f85b8bf

Subscribe to this mod's changes

clare2-corpus-capture is a command published in the GitHub repository jketreno/clare (5 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 989 once invoked, about $0.0001 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 2026-08-31.