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/ashlrai/ashlr-plugin/ashlr-briefgit clone --depth 1 https://github.com/ashlrai/ashlr-pluginWrote 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/ashlrai/ashlr-plugin/ashlr-brief)<a href="https://agentmods.dev/commands/ashlrai/ashlr-plugin/ashlr-brief"><img src="https://agentmods.dev/badge/commands/ashlrai/ashlr-plugin/ashlr-brief.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.01050 |
| Opus 5 | $0.00029 | $0.00525 |
| Sonnet 5 | $0.00012 | $0.00210 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
ashlr-brief 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 5d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Toggle ashlr-brief — a tunable, opt-in response-shortening layer. Free users get user-level preferences; Pro/Team users get project-level enforcement.
Usage
/ashlr-brief on # enable at default level (standard)
/ashlr-brief on lite # mild trim — keeps full grammar
/ashlr-brief on standard # default — drop padding
/ashlr-brief on concise # max — fragments + arrows allowed
/ashlr-brief off # disable
/ashlr-brief status # show current level + active source
/ashlr-brief --project standard # write `.ashlr/brief.json` (Pro/Team only)
What it does
| Level | Reduction | Effect |
|---|---|---|
lite |
~25–35% | Drops filler; keeps full grammar |
standard (default) |
~35–45% | Drops padding + transitions; keeps grammar |
concise |
~50–60% | Fragments + arrows OK; abbreviations allowed for prose only |
Code blocks, error messages, file paths, and destructive-action confirmations are always rendered in full grammar regardless of level. See skills/ashlr-brief/SKILL.md for the full ruleset.
Steps
on [level]
- Default level if omitted:
standard. Validate level is one oflite | standard | concise. - Write to
~/.ashlr/brief.json:
Use{ "level": "standard", "setAt": "<ISO8601>", "source": "user" }mkdir -p ~/.ashlrfirst if needed. - Print:
ashlr-brief: <level> ON. Effective on the next response. - Code blocks, errors, and destructive confirmations remain in full grammar. - Status line shows `[brief: <level>]` while active. Toggle off with: /ashlr-brief off
off
- Write to
~/.ashlr/brief.json:{ "level": "off", "setAt": "<ISO8601>", "source": "user" } - Print:
ashlr-brief: OFF. Default verbosity restored.
status
- Read
~/.ashlr/brief.json(level field). - Read
<repo-root>/.ashlr/brief.jsonif present (project override). - Print:
If no file exists for either, showashlr-brief status user-level: <level> (~/.ashlr/brief.json) project-level: <level> (.ashlr/brief.json) — Pro-enforced effective: <project wins if Pro-set, else user><not set>.
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.
- 5d ago First seen · 98 lines · 58 tokens per session scan A ce100446c971
ashlr-brief is a command published in the GitHub repository ashlrai/ashlr-plugin (3 stars, last pushed 5d ago), licensed MIT. It adds 58 tokens to every session and 1,050 once invoked, about $0.0003 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.
Other commands, from other repositories
vibegroup
Work with your vibegroup room (peers, ask, inbox, status).
cancel-ralph
Cancel active Ralph Loop.
changelog
Generate a changelog for version $ARGUMENTS by analyzing git history.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.
tree
Show file tree with sync status indicators showing which files are indexed, modified, new, or deleted.
focus
You are an ADHD focus assistant. Help the user commit to ONE task and block mental distractions.