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 skills/ashlrai/ashlr-plugin/ashlr-efficientnpx skills add ashlrai/ashlr-plugin --skill ashlr-efficientgit 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-efficient)<a href="https://agentmods.dev/skills/ashlrai/ashlr-plugin/ashlr-efficient"><img src="https://agentmods.dev/badge/skills/ashlrai/ashlr-plugin/ashlr-efficient.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 | $0.00055 | $0.00744 |
| Opus 5 | $0.00028 | $0.00372 |
| Sonnet 5 | $0.00011 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade C, and why
ashlr-efficient scanned grade C 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 3d 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 deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Destructive actions (`rm -rf`, `git reset --hard`, force-push, `DROP TABLE`) How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ashlr Efficient
Reshapes the structure of responses — not just their wordiness. Works independently of ashlr-brief (which trims prose volume). When both are active, both rulesets apply simultaneously.
Rules (active when this skill is enabled)
1. Inverted pyramid — answer first
Lead with the answer or conclusion. Context and explanation follow. Never open with background before the answer.
Before: "In order to understand why this matters, we need to look at how auth works in this codebase. The token is validated in middleware..."
After: "The verifyToken middleware at src/auth.ts:42 is the validation point. It checks..."
2. Inline code for all identifiers and paths
Any function name, variable, type, file path, CLI command, or config key appears in backtick inline code — never in plain prose.
Before: "The handleAuth function in the auth file calls verifyToken."
After: "handleAuth in src/auth.ts calls verifyToken."
3. Tables for 3+ item comparisons
When comparing 3 or more options, tools, config values, or behaviors — use a markdown table, not a bulleted prose list.
Before:
ashlr__editis for single editsashlr__multi_editis for multiple edits to one fileashlr__edit_structuralis for renames
After:
| Tool | Use case |
|---|---|
ashlr__edit |
Single search/replace |
ashlr__multi_edit |
Multiple edits, one file |
ashlr__edit_structural |
Symbol/file renames |
4. No transitional filler
Drop: "Now that we've seen X, let's look at Y", "As mentioned above", "Moving on to", "Let's now", "With that in mind", "That said". Just move to the next point.
5. file:line citations instead of quoted blocks
When pointing to code, use path/to/file.ts:42 format. Only quote the exact lines when they are load-bearing to the explanation (e.g., a bug pattern, a function signature the user asked for).
Auto-clarity exceptions (full structure restored)
These contexts always get full explanatory structure regardless of the efficient level:
- Destructive actions (
rm -rf,git reset --hard, force-push,DROP TABLE) - Security findings (credentials, secrets, vulnerabilities)
- Error messages and stack traces (rendered verbatim)
- Multi-step migrations where sequence matters
- Code blocks and diffs (pass through untouched)
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.
- 3d ago First seen · 65 lines · 55 tokens per session scan C 31395223e10d
ashlr-efficient is a skill published in the GitHub repository ashlrai/ashlr-plugin (3 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 744 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C 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
rust-system-calls
Guides using bunsys for system calls and file I/O in Rust. Use when implementing file operations, opening fds, or any syscall path instead of std::fs or libc.
bunqueue-dev
Internal skill for contributing to bunqueue - architecture, testing, code conventions, and development workflow.
google-meet
Google Meet via gws: create spaces, fetch join links, list recordings.
people-crm
Turn LinkedIn connections (or any contact export) into a queryable personal CRM using the agent database.
clarify-spec
Full execution protocol for MODE: CLARIFY-SPEC -- resolving spec clarification markers and maintaining spec/planning alignment.
swarm-implement
Codex adapter for complex implementation work using the canonical opencode-swarm implementation workflow. Use for multi-file features, bug fixes, refactors, risky code changes, or tasks that benefit from exploration, scoped planning, implementation, review, and validation.