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-lean-toolsgit 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-lean-tools)<a href="https://agentmods.dev/skills/ashlrai/ashlr-plugin/ashlr-lean-tools"><img src="https://agentmods.dev/badge/skills/ashlrai/ashlr-plugin/ashlr-lean-tools/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/skills/ashlrai/ashlr-plugin/ashlr-lean-tools"><img src="https://agentmods.dev/badge/skills/ashlrai/ashlr-plugin/ashlr-lean-tools.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 | $0.00052 | $0.00628 |
| Opus 5.5 | $0.00021 | $0.00251 |
| Sonnet 5.5 | $0.00010 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
ashlr-lean-tools 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 1mo 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ashlr Lean Tools
A discipline layer for tool use: each rule targets a specific token-waste pattern that commonly appears in long sessions.
Rules (active when this skill is enabled)
1. Read-once
Do not re-read a file that is already in context. If you opened src/auth.ts earlier this session and haven't been told it changed, use the content you already have. Re-reads are the single largest source of avoidable input-token spend.
2. Batch edits via ashlr__multi_edit
When making 2+ edits to the same file, collect them into a single ashlr__multi_edit call instead of sequential ashlr__edit calls. Multi-edit applies all changes in one round-trip and returns a single compact diff.
3. Orient before searching
Run ashlr__orient once at the start of each task. The genome overview typically resolves "where does X live?" without any file reads. Skip orient only when continuing work in a file you already have open.
4. Skip verification reads after a successful edit/write
ashlr__edit and ashlr__write confirm success by returning a diff. Do not read the file again just to confirm the change landed — that's redundant and costs the full file content in tokens.
5. Grep-before-read
Before opening a file to find something, run ashlr__grep first. If the grep result shows the relevant lines, use them directly — no full file read needed.
6. Shift to concise output when session spend is high
When the session has accumulated >5,000 tokens of tool-call output, prefer shorter responses: skip preamble, use file:line citations instead of quoted blocks, and omit trailing summaries when the diff speaks for itself.
7. Prefer ashlr__bash over native Bash for verbose commands
ashlr__bash auto-compresses long stdout (test runners, git log, find, npm ls) — 60–90% token savings on large output.
Anti-patterns
- Re-reading a file that hasn't changed since you last read it
- Two sequential
ashlr__editcalls on the same file (useashlr__multi_edit) - Opening a file just to confirm an edit you just made
- Running
ReadbeforeGrepto find a function - Quoting large file contents in prose when a
file:linereference suffices
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.
- 1mo ago First seen · 44 lines · 52 tokens per session scan A e34caa5c7852
ashlr-lean-tools is a skill published in the GitHub repository ashlrai/ashlr-plugin (3 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 628 once invoked, about $0.0002 per session on Opus 5.5. 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 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…
monday-planning
Suggest a weekly training structure from recent load and deliver the plan.
fresh-start
Continue in a new chat without losing anything — writes a compact handoff to paste into a fresh conversation. Use whenever the user wants to move to a new chat or conversation, hits usage limits, says replies got slow or Claude forgets earlier details, or the conversation has grown long.
token-check
Estimate how many tokens a pasted text, an attached file or the conversation so far takes, what it means for the context window and usage limits, and how to cut it. Use when the user asks how big something is in tokens, why they keep hitting limits, or whether a file is too large to send.
ritual
Discover recurring behaviors from memory and offer to formalize them as scheduled jobs.
overheard
Find commitments the user made in the last two weeks and did not follow through on. A promises audit.