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 skills add ashlrai/ashlr-plugin --skill 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/skills/ashlrai/ashlr-plugin/ashlr-brief)<a href="https://agentmods.dev/skills/ashlrai/ashlr-plugin/ashlr-brief"><img src="https://agentmods.dev/badge/skills/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 5.1 | $0.00063 | $0.01184 |
| Opus 5 | $0.00032 | $0.00592 |
| Sonnet 5 | $0.00013 | $0.00237 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade B, and why
ashlr-brief scanned grade B with 1 finding 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 8d 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
1. **Destructive actions** — `rm -rf`, `git reset --hard`, `git push --force`, `DROP TABLE`, dropping migrations, deleting branches, killing processes Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ashlr Brief
Reduce token spend by trimming Claude's output, not just tool I/O. Inspired by Julius Brussee's caveman, but designed to remain readable in PRs, code reviews, and explanations — full grammar at the default level, no telegraphic "caveman voice" unless explicitly opted into.
Activation
Three ways to activate:
- Slash command —
/ashlr-brief on standard - Natural language — "be brief", "tldr", "less tokens", "stop being brief"
- Eco mode —
/ashlr-eco-mode onauto-activatesstandardif no level is already chosen
Persistence: the active level is written to ~/.ashlr/brief.json and re-injected on every SessionStart, so behavior stays stable across sessions until explicitly changed.
Intensity levels
lite — professional terseness
- Drop: filler ("just", "really", "basically", "actually", "simply", "essentially", "in order to"), hedging ("might possibly", "I think it could"), self-narration ("Let me look at...", "I'll now...")
- Keep: articles, complete sentences, paragraph breaks, full grammar, all explanations the user asked for
- Tone: professional, direct, like a senior engineer in a code review
- Expected output reduction: ~25–35%
standard — default — drop padding, keep grammar
- All of
lite, plus: - Drop transition padding ("Now that we have X, let's move on to Y", "As you can see")
- Replace verbose constructions with short ones ("in order to" → "to", "due to the fact that" → "because")
- Cut restating-the-question preambles
- One-sentence summaries instead of "Here's what I did:" lists when the diff already shows it
- Keep: complete sentences, articles, code blocks untouched
- Expected output reduction: ~35–45%
concise — fragments + arrows allowed
- All of
standard, plus: - Sentence fragments OK when meaning is clear
- Arrow notation for causality (
X → Yinstead of "X causes Y") - Common abbreviations OK (
db,auth,cfg,req,res,fn,ctx) - Bullets over prose for lists of 3+
- Keep: Code blocks, error messages, file paths, identifiers — never abbreviated
- Expected output reduction: ~50–60%
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.
- 8d ago First seen · 81 lines · 63 tokens per session scan B b57866aa8701
ashlr-brief is a skill published in the GitHub repository ashlrai/ashlr-plugin (3 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 1,184 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
familiar-help
Use familiar companion tools for creative buddy/companion interactions. Handles fortunes, code roasts, haiku, stats, mood, lore, focus timers, and personality changes. Triggers when user addresses their companion by any name — "buddy" (Anthropic's UI label), "familiar", "companion", or whatever name the user uses for…
doctor-dashi-plugin
Diagnose and safely complete a migration from the legacy Telegram gateway to the dashi-plugin-claude-code channel. Use this whenever an agent is moving off the old gateway, when a freshly migrated bot is silent / hangs / answers as "default Claude", when you hit a Telegram 409 conflict, or when planning the cutover.…
img-pilot
AI-generated brand assets (logo, favicon, social, banner, icons) from Claude Code. Reads ux-pilot and brand-pilot briefs automatically. 9 providers, cost-optimized.
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
test-run
Run plugin test suites in this monorepo and report a concise pass/fail summary. Optional plugin slug arg; without arg, runs all plugins under plugins/.