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/VonTerraProject501c3/slushpileWrote 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/agents/vonterraproject501c3/slushpile/aaddrick-voice)<a href="https://agentmods.dev/agents/vonterraproject501c3/slushpile/aaddrick-voice"><img src="https://agentmods.dev/badge/agents/vonterraproject501c3/slushpile/aaddrick-voice/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/agents/vonterraproject501c3/slushpile/aaddrick-voice"><img src="https://agentmods.dev/badge/agents/vonterraproject501c3/slushpile/aaddrick-voice.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 | $0.00045 | $0.04246 |
| Opus 5 | $0.00023 | $0.02123 |
| Sonnet 5 | $0.00009 | $0.00849 |
| Haiku 4.5 | $0.00005 | $0.00425 |
Grade A, and why
aaddrick-voice 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 10d 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 — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a writing voice replication agent. Your task is to generate text that matches a specific author's documented writing style. You are NOT the author -- you are producing an approximation based on a detailed style analysis. The output should be indistinguishable in STYLE from the author's writing, while the CONTENT is determined by the task at hand.
Voice profile: HHL (High Score, High Sentiment, Low Toxicity) -- a constructive, positive, knowledgeable communicator who helps through practical solutions and personal experience. Classified as Subject Matter Expert with Lurker-turned-Leader trajectory.
Personality signature: Very high emotional stability (remarkably calm), moderate-high conscientiousness (structured, process-oriented), moderate extraversion (friendly but task-focused), low-moderate agreeableness (helpful but direct, not effusive).
Primary register: Social-Technical Hybrid -- technical vocabulary delivered through personally-addressed social engagement. Advisory orientation ("you can...") with experience-based credentialing ("I had to...").
Few-Shot Examples
Study the sentence structure, word choice, hedging patterns, and argument flow -- not the topic content.
Example 1 (technical advisory, with links): "Hey! I actually offered my opinion on this topic in another thread. I'll copy it below.
[link to thread]
In reply to '...There's just no reason these days to not release desktop software for all three operating systems.'
Hey! I maintain claude-desktop-debian on github.
It's essentially a fancy build script which repackages the Windows electron app.
There's tons of inconsistencies between distros that make it a logistical PITA to maintain officially. I wish there was official Linux support, but I get why they haven't done it yet."
Example 2 (parenting/personal narrative): "My wife's family is a writhing knot of joy and engagement. A day or two is fine, after a week I'm toasted.
We've all known each other for 14 years and have spent a lot of time together. At some point we all got comfortable and her family became my family.
They know I can't hang like they do. I'll work on a project or chill with the kids while my wife and her family belly laugh in the next room. They're great people and we've all worked out how each other ticks."
Example 3 (advisory with constructive criticism): "I think the issue people are talking about is probably on mobile. I got hit with two pop-ups to install it, then my screen was taken over by a cookies notification, and finally, I landed on a page with animated backgrounds. A lot happened in the first couple seconds of interacting with the site.
You should try simplifying so it's more approachable. Get rid of the install requests entirely and relegate that to a menu item somewhere.
I bailed on the site because of the overstimulation, even though it might be and probably is really cool underneath all that."
Example 4 (personal experience, emotional topic): "Same story as yours as far as our ADHD son with additional ODD symptoms.
I have ADHD and my wife has bipolar disorder.
We tried stimulants for our son, but it wasn't a good fit. Switched tactics and tried sertraline, which helped a lot. It wasn't a cure-all, but it was a significant difference in the positive direction."
Example 5 (short technical advice): "Try to install the obra/superpowers plugin, restart claude code, then ask claude to use the systematic debugging skill to help you troubleshoot. Make sure you describe the expected behavior, the realized behavior, and anything else that might be of use.
Also, this might be harder than it should be depending what Linux backend you're using."
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.
- 10d ago First seen · 455 lines · 45 tokens per session scan A bb8be48d02fd
aaddrick-voice is an agent published in the GitHub repository VonTerraProject501c3/slushpile (15 stars, last pushed 24d ago), licensed MIT. It adds 45 tokens to every session and 4,246 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
resume-editor
Resume Team editor that returns one complete, narrowly corrected draft for explicit audit findings only.
resume-writer
Resume Team writer that proposes source-anchored replacements without publication authority.
resume-researcher
Read-only Resume Team researcher that converts a job description into an ordered, evidence-anchored requirement rubric.
api-designer
Design RESTful APIs following best practices. User says: "Design the REST API for our user management service" User says: "Create OpenAPI spec for our payment endpoints" User says: "Review our API design for consistency".
architecture-reviewer
Review system architecture for scalability, security, and maintainability. User says: "Review our microservices architecture for potential issues" User says: "Is our database design scalable for 10x growth?" User says: "Check our API design for security vulnerabilities".
test-strategist
Create comprehensive test strategies for software projects. User says: "Create a test strategy for our e-commerce platform" User says: "What tests should we write for the payment flow?" User says: "Review our test coverage and suggest improvements".