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.
git clone --depth 1 https://github.com/mturac/everything-openai-codexWrote 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.
[](https://agentmods.dev/commands/mturac/everything-openai-codex/prune)<a href="https://agentmods.dev/commands/mturac/everything-openai-codex/prune"><img src="https://agentmods.dev/badge/commands/mturac/everything-openai-codex/prune/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.
<a href="https://agentmods.dev/commands/mturac/everything-openai-codex/prune"><img src="https://agentmods.dev/badge/commands/mturac/everything-openai-codex/prune.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.00174 |
| Opus 5 | $0.00008 | $0.00087 |
| Sonnet 5 | $0.00003 | $0.00035 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
prune scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Prune Pending Instincts
Remove expired pending instincts that were auto-generated but never reviewed or promoted.
Implementation
Run the instinct CLI using the plugin root path:
python3 "${CODEX_PLUGIN_ROOT}/skills/continuous-learning-v2/scripts/instinct-cli.py" prune
Or if CODEX_PLUGIN_ROOT is not set (manual installation):
python3 ~/.codex/skills/continuous-learning-v2/scripts/instinct-cli.py prune
Usage
/prune # Delete instincts older than 30 days
/prune --max-age 60 # Custom age threshold (days)
/prune --dry-run # Preview without deleting
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.
- 6d ago First seen · 32 lines · 15 tokens per session scan A 4fc9c7f78e90
prune is a command published in the GitHub repository mturac/everything-openai-codex (90 stars, last pushed 16d ago), licensed MIT. It adds 15 tokens to every session and 174 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 2026-09-03.
Other commands, from other repositories
help
Explain Ralph Wiggum technique and available commands.
install
Guided setup for a new Cowork workspace. Interviews you (about 5 minutes) and generates a full, pre-configured cowork-os workspace (folders, copy, project instructions, and recurring routines).
aside
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.